diff --git a/nemo_deploy/llm/inference/inference_base.py b/nemo_deploy/llm/inference/inference_base.py index cd207965d..e12f56f33 100644 --- a/nemo_deploy/llm/inference/inference_base.py +++ b/nemo_deploy/llm/inference/inference_base.py @@ -27,7 +27,10 @@ get_default_load_sharded_strategy, ) from megatron.core.dist_checkpointing.validation import StrictHandling +from megatron.core.inference.config import InferenceConfig +from megatron.core.inference.contexts.dynamic_context import DynamicInferenceContext from megatron.core.inference.contexts.static_context import StaticInferenceContext +from megatron.core.inference.engines.dynamic_engine import DynamicInferenceEngine from megatron.core.inference.engines.mcore_engine import MCoreEngine from megatron.core.inference.model_inference_wrappers.gpt.gpt_inference_wrapper import ( GPTInferenceWrapper, @@ -229,18 +232,27 @@ def setup_megatron_model_and_tokenizer_for_inference( torch_distributed_init(dist_config) model_config, mlm_args = load_model_config(checkpoint_path) + # MLA models require cache_mla_latents=True for the dynamic inference backend. + # The checkpoint may have saved it as False (training default), but inference + # with the dynamic engine always needs it enabled. + if hasattr(model_config, "cache_mla_latents"): + model_config.cache_mla_latents = True + # Convert attention_backend from string to enum if needed - if hasattr(model_config, "attention_backend") and isinstance(model_config.attention_backend, str): - if model_config.attention_backend == "AttnBackend.fused": - model_config.attention_backend = AttnBackend.fused - elif model_config.attention_backend == "AttnBackend.flash": - model_config.attention_backend = AttnBackend.flash - elif model_config.attention_backend == "AttnBackend.unfused": - model_config.attention_backend = AttnBackend.unfused - elif model_config.attention_backend == "AttnBackend.local": - model_config.attention_backend = AttnBackend.local - elif model_config.attention_backend == "AttnBackend.auto": + if hasattr(model_config, "attention_backend"): + if model_config.attention_backend is None: + # Deserialization of the AttnBackend enum failed (e.g. Hydra _target_ dict + # not reconstructed); fall back to auto so the engine can pick the best backend. model_config.attention_backend = AttnBackend.auto + elif isinstance(model_config.attention_backend, str): + _str_to_attn_backend = { + "AttnBackend.fused": AttnBackend.fused, + "AttnBackend.flash": AttnBackend.flash, + "AttnBackend.unfused": AttnBackend.unfused, + "AttnBackend.local": AttnBackend.local, + "AttnBackend.auto": AttnBackend.auto, + } + model_config.attention_backend = _str_to_attn_backend.get(model_config.attention_backend, AttnBackend.auto) if tensor_model_parallel_size is not None: model_config.tensor_model_parallel_size = tensor_model_parallel_size @@ -524,6 +536,35 @@ def create_mcore_engine( buffer_size_gb=buffer_size_gb, ) + # MCoreEngine (StaticInferenceEngine) initialises its DynamicInferenceContext with + # block_size_tokens=256. MLA models require block_size_tokens=64 (Flash MLA), so the + # init silently fails and the engine falls back to legacy static batching — which is + # incompatible with cache_mla_latents=True. Detect that fallback and redo the dynamic + # engine setup with the correct block size. + if getattr(model.config, "cache_mla_latents", False) and mcore_engine.legacy: + LOGGER.info( + "MCoreEngine fell back to legacy static engine for MLA model; " + "reinitialising DynamicInferenceEngine with block_size_tokens=64." + ) + dynamic_context = DynamicInferenceContext( + model_config=model.config, + inference_config=InferenceConfig( + max_sequence_length=inference_max_seq_length, + buffer_size_gb=buffer_size_gb, + max_requests=max_batch_size, + num_cuda_graphs=1, + block_size_tokens=64, # Flash MLA requirement + unified_memory_level=0, + ), + ) + mcore_engine.controller.inference_wrapped_model.inference_context = dynamic_context + mcore_engine.controller.inference_wrapped_model.prep_model_for_inference() + mcore_engine.controller._init_dynamic_sampling_tensors() + mcore_engine.dynamic_engine = DynamicInferenceEngine( + controller=mcore_engine.controller, context=dynamic_context + ) + mcore_engine.legacy = False + # Wrap the engine to ensure cleanup wrapped_engine = MCoreEngineWithCleanup(mcore_engine, model_inference_wrapper, tokenizer) diff --git a/pyproject.toml b/pyproject.toml index 91b1d05d8..d8737c77e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -149,11 +149,14 @@ override-dependencies = [ "flash-linear-attention>=0.3.0,<0.4.dev0", "patchelf; sys_platform=='never'", "nvidia-resiliency-ext>=0.3.0,<0.6.0", - "transformer-engine[pytorch,core_cu13]>=2.12.0a0,<2.15.0; sys_platform != 'darwin'", - "transformer-engine-cu13>=2.12.0a0,<2.15.0; sys_platform != 'darwin'", "transformer-engine-cu12; sys_platform == 'never'", + # The custom-built TE in the container already includes the torch extension natively. + # Installing transformer-engine-torch from PyPI creates a dist-info that triggers TE's + # sanity check requiring the base package to also be a PyPI wheel, which fails for + # source/custom builds. Since the .so is already present, skip the PyPI package. + "transformer-engine-torch; sys_platform == 'never'", "mamba-ssm>=2.3.0,<2.4.0", - "transformers>=5.0.0", + "transformers==5.2.0", "protobuf~=6.33.5", "opencv-python-headless; sys_platform == 'never'", "cryptography>=43.0.0,<47", diff --git a/uv.lock b/uv.lock index 57fc1ebb5..bed55a7e6 100644 --- a/uv.lock +++ b/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 3 +revision = 2 requires-python = ">=3.10, <3.13" resolution-markers = [ "python_full_version >= '3.12' and platform_machine == 'aarch64' and sys_platform == 'linux' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra != 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm'", @@ -79,10 +79,9 @@ overrides = [ { name = "torch", marker = "sys_platform == 'never'", index = "https://download.pytorch.org/whl/cu130" }, { name = "torchvision", marker = "sys_platform == 'never'" }, { name = "transformer-engine", extras = ["pytorch"], specifier = ">=2.12.0a0,<2.14.0" }, - { name = "transformer-engine", extras = ["pytorch", "core-cu13"], marker = "sys_platform != 'darwin'", specifier = ">=2.12.0a0,<2.15.0" }, { name = "transformer-engine-cu12", marker = "sys_platform == 'never'" }, - { name = "transformer-engine-cu13", marker = "sys_platform != 'darwin'", specifier = ">=2.12.0a0,<2.15.0" }, - { name = "transformers", specifier = ">=5.0.0" }, + { name = "transformer-engine-torch", marker = "sys_platform == 'never'" }, + { name = "transformers", specifier = "==5.2.0" }, { name = "triton", marker = "sys_platform == 'never'" }, { name = "urllib3", specifier = ">1.27.0" }, ] @@ -107,7 +106,7 @@ dependencies = [ { name = "psutil" }, { name = "pyyaml" }, { name = "safetensors" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/b1/72/ff3961c19ee395c3d30ac630ee77bfb0e1b46b87edc504d4f83bb4a89705/accelerate-1.10.1.tar.gz", hash = "sha256:3dea89e433420e4bfac0369cae7e36dcd6a56adfcfd38cdda145c6225eab5df8", size = 392446, upload-time = "2025-08-25T13:57:06.21Z" } wheels = [ @@ -199,7 +198,7 @@ source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohappyeyeballs" }, { name = "aiosignal" }, - { name = "async-timeout", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "async-timeout", marker = "python_full_version < '3.11'" }, { name = "attrs" }, { name = "frozenlist" }, { name = "multidict" }, @@ -376,7 +375,7 @@ name = "anyio" version = "4.11.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "exceptiongroup", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "exceptiongroup", marker = "python_full_version < '3.11'" }, { name = "idna" }, { name = "sniffio" }, { name = "typing-extensions" }, @@ -960,7 +959,7 @@ name = "cffi" version = "2.0.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "pycparser", marker = "implementation_name != 'PyPy' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "pycparser", marker = "implementation_name != 'PyPy'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/eb/56/b1ba7935a17738ae8453301356628e8147c79dbb825bcbc73dc7401f9846/cffi-2.0.0.tar.gz", hash = "sha256:44d1b5909021139fe36001ae048dbdde8214afa20200eda0f64c068cac5d5529", size = 523588, upload-time = "2025-09-08T23:24:04.541Z" } wheels = [ @@ -1059,7 +1058,7 @@ name = "click" version = "8.3.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/46/61/de6cd827efad202d7057d93e0fed9294b96952e188f7384832791c7b2254/click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4", size = 276943, upload-time = "2025-09-18T17:32:23.696Z" } wheels = [ @@ -1161,7 +1160,7 @@ resolution-markers = [ "python_full_version < '3.11' and sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra != 'extra-18-nemo-export-deploy-trtllm' and extra != 'extra-18-nemo-export-deploy-vllm'", ] dependencies = [ - { name = "numpy", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "numpy", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/66/54/eb9bfc647b19f2009dd5c7f5ec51c4e6ca831725f1aea7a993034f483147/contourpy-1.3.2.tar.gz", hash = "sha256:b6945942715a034c671b7fc54f9588126b0b8bf23db2696e3ca8328f3ff0ab54", size = 13466130, upload-time = "2025-04-15T17:47:53.79Z" } wheels = [ @@ -1242,7 +1241,7 @@ resolution-markers = [ "python_full_version == '3.11.*' and sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra != 'extra-18-nemo-export-deploy-trtllm' and extra != 'extra-18-nemo-export-deploy-vllm'", ] dependencies = [ - { name = "numpy", marker = "python_full_version >= '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "numpy", marker = "python_full_version >= '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/58/01/1253e6698a07380cd31a736d248a3f2a50a7c88779a1813da27503cadc2a/contourpy-1.3.3.tar.gz", hash = "sha256:083e12155b210502d0bca491432bb04d56dc3432f95a979b429f2848c3dbe880", size = 13466174, upload-time = "2025-07-26T12:03:12.549Z" } wheels = [ @@ -1327,8 +1326,8 @@ name = "cryptography" version = "46.0.5" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "cffi", marker = "platform_python_implementation != 'PyPy' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "typing-extensions", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "cffi", marker = "platform_python_implementation != 'PyPy'" }, + { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/60/04/ee2a9e8542e4fa2773b81771ff8349ff19cdd56b7258a0cc442639052edb/cryptography-46.0.5.tar.gz", hash = "sha256:abace499247268e3757271b2f1e244b36b06f8515cf27c4d49468fc9eb16e93d", size = 750064, upload-time = "2026-02-10T19:18:38.255Z" } wheels = [ @@ -1373,7 +1372,7 @@ name = "cuda-bindings" version = "13.1.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "cuda-pathfinder", marker = "sys_platform != 'darwin' or extra == 'extra-18-nemo-export-deploy-trtllm' or extra == 'extra-18-nemo-export-deploy-vllm'" }, + { name = "cuda-pathfinder" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/60/63/579402b642f5b9b8ceb79e456b39b5771f27e132a8af3b140e54d69790fc/cuda_bindings-13.1.1-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4400370a83f1538e25ed4c18c34a0e9d5fad39741e282e69ce24d1479a11017d", size = 15777291, upload-time = "2025-12-09T22:05:41.109Z" }, @@ -1770,7 +1769,7 @@ name = "exceptiongroup" version = "1.3.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "typing-extensions", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/0b/9f/a65090624ecf468cdca03533906e7c69ed7588582240cfe7cc9e770b50eb/exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88", size = 29749, upload-time = "2025-05-10T17:42:51.123Z" } wheels = [ @@ -2013,7 +2012,7 @@ dependencies = [ { name = "pynvml" }, { name = "requests" }, { name = "tabulate" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, { name = "tqdm" }, ] sdist = { url = "https://files.pythonhosted.org/packages/49/a7/f5bd3878f94fc47e25ecc0828f910233022366f7e832dfa02f3617fad41f/flashinfer_python-0.3.1.post1.tar.gz", hash = "sha256:d32218c7e33bcbf907719d3e51ddbea84d94a87fd0425378d70bcd28728f342e", size = 3817448, upload-time = "2025-09-26T04:26:25.177Z" } @@ -2747,7 +2746,7 @@ source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "filelock" }, { name = "fsspec", extra = ["http"] }, - { name = "hf-xet", marker = "platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "hf-xet", marker = "platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'" }, { name = "httpx" }, { name = "packaging" }, { name = "pyyaml" }, @@ -3842,7 +3841,6 @@ dependencies = [ { name = "timm" }, { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "tqdm" }, - { name = "transformer-engine", extra = ["core-cu13"], marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "transformer-engine", extra = ["pytorch"] }, { name = "transformers" }, { name = "typing-extensions" }, @@ -3884,7 +3882,6 @@ dev = [ { name = "quart" }, { name = "tensorstore" }, { name = "tqdm" }, - { name = "transformer-engine", extra = ["core-cu13"], marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "transformer-engine", extra = ["pytorch"] }, { name = "wget" }, ] @@ -4126,7 +4123,7 @@ name = "mlx" version = "0.29.2" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "mlx-metal", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, + { name = "mlx-metal", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/3f/f0/2c2f99a91ed9dfcc78d31d9e5d3bb2f5305a8d65953cbc41f34f8056c49a/mlx-0.29.2-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:b46c1a24b9b8f7145e4d84410552ddfa03f40f9afdbe8f819f6b4b52b4db5d30", size = 547369, upload-time = "2025-09-26T22:21:33.668Z" }, @@ -4148,12 +4145,12 @@ name = "mlx-lm" version = "0.28.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "jinja2", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, - { name = "mlx", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, - { name = "numpy", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, - { name = "protobuf", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, - { name = "pyyaml", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, - { name = "transformers", marker = "(platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine != 'aarch64' and sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_machine == 'aarch64' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform != 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm')" }, + { name = "jinja2", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, + { name = "mlx", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, + { name = "numpy", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, + { name = "protobuf", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, + { name = "pyyaml", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, + { name = "transformers", marker = "platform_machine != 'aarch64' and sys_platform == 'darwin'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/41/3b/4d03bef1372f079f64bba6e6dc8b6a545f1e71b8b7d101bccfa9c86977a5/mlx_lm-0.28.1.tar.gz", hash = "sha256:4d67e6eb2a4d1aca91d199dbacc52817526ff236b34d08b31a90f510d52703c2", size = 208979, upload-time = "2025-09-27T02:23:58.804Z" } wheels = [ @@ -4349,7 +4346,7 @@ name = "multidict" version = "6.6.4" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "typing-extensions", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/69/7f/0652e6ed47ab288e3756ea9c0df8b14950781184d4bd7883f4d87dd41245/multidict-6.6.4.tar.gz", hash = "sha256:d2d4e4787672911b48350df02ed3fa3fffdc2f2e8ca06dd6afdf34189b76a9dd", size = 101843, upload-time = "2025-08-11T12:08:48.217Z" } wheels = [ @@ -4496,7 +4493,6 @@ dependencies = [ { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "torchmetrics" }, { name = "torchvision", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "transformer-engine", extra = ["core-cu13"], marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "transformer-engine", extra = ["pytorch"] }, { name = "uvicorn" }, { name = "wandb" }, @@ -5156,7 +5152,7 @@ name = "nvdlfw-inspect" version = "0.2.2" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "pyyaml" }, + { name = "pyyaml", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, ] wheels = [ @@ -5305,7 +5301,7 @@ dependencies = [ { name = "safetensors" }, { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "scipy", version = "1.16.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, { name = "torchprofile" }, { name = "tqdm" }, ] @@ -6039,7 +6035,7 @@ dependencies = [ { name = "psutil" }, { name = "pyyaml" }, { name = "safetensors" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, { name = "tqdm" }, { name = "transformers" }, ] @@ -7030,7 +7026,7 @@ name = "pyzmq" version = "27.1.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "cffi", marker = "(implementation_name == 'pypy' and sys_platform != 'darwin') or (implementation_name == 'pypy' and extra == 'extra-18-nemo-export-deploy-trtllm') or (implementation_name == 'pypy' and extra == 'extra-18-nemo-export-deploy-vllm') or (implementation_name != 'pypy' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (implementation_name != 'pypy' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (implementation_name != 'pypy' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "cffi", marker = "implementation_name == 'pypy'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/04/0b/3c9baedbdf613ecaa7aa07027780b8867f57b6293b6ee50de316c9f3222b/pyzmq-27.1.0.tar.gz", hash = "sha256:ac0765e3d44455adb6ddbf4417dcce460fc40a05978c08efdf2948072f6db540", size = 281750, upload-time = "2025-09-08T23:10:18.157Z" } wheels = [ @@ -7743,7 +7739,7 @@ resolution-markers = [ "python_full_version < '3.11' and sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra != 'extra-18-nemo-export-deploy-trtllm' and extra != 'extra-18-nemo-export-deploy-vllm'", ] dependencies = [ - { name = "numpy", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "numpy", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6964b830433e654ec7485e45a00fc9a27cf868d622838f6b6d9c5ec0d532/scipy-1.15.3.tar.gz", hash = "sha256:eae3cf522bc7df64b42cad3925c876e1b0b6c35c1337c93e12c0f366f55b0eaf", size = 59419214, upload-time = "2025-05-08T16:13:05.955Z" } wheels = [ @@ -7815,7 +7811,7 @@ resolution-markers = [ "python_full_version == '3.11.*' and sys_platform == 'darwin' and extra != 'extra-18-nemo-export-deploy-trt-onnx' and extra != 'extra-18-nemo-export-deploy-trtllm' and extra != 'extra-18-nemo-export-deploy-vllm'", ] dependencies = [ - { name = "numpy", marker = "python_full_version >= '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "numpy", marker = "python_full_version >= '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/4c/3b/546a6f0bfe791bbb7f8d591613454d15097e53f906308ec6f7c1ce588e8e/scipy-1.16.2.tar.gz", hash = "sha256:af029b153d243a80afb6eabe40b0a07f8e35c9adc269c019f364ad747f826a6b", size = 30580599, upload-time = "2025-09-11T17:48:08.271Z" } wheels = [ @@ -8463,7 +8459,7 @@ name = "sympy" version = "1.14.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "mpmath", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "mpmath", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/83/d3/803453b36afefb7c2bb238361cd4ae6125a569b4db67cd9e79846ba2d68c/sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517", size = 7793921, upload-time = "2025-04-27T18:05:01.611Z" } wheels = [ @@ -8892,8 +8888,8 @@ dependencies = [ { name = "huggingface-hub" }, { name = "pyyaml" }, { name = "safetensors" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "torchvision", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, + { name = "torchvision", marker = "sys_platform == 'never'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/b5/ba/6f5d96622a4a9fc315da53f58b3ca224c66015efe40aa191df0d523ede7c/timm-1.0.20.tar.gz", hash = "sha256:7468d32a410c359181c1ef961f49c7e213286e0c342bfb898b99534a4221fc54", size = 2360052, upload-time = "2025-09-21T17:26:35.492Z" } wheels = [ @@ -8968,15 +8964,15 @@ name = "torch" version = "2.9.0+cu130" source = { registry = "https://download.pytorch.org/whl/cu130" } dependencies = [ - { name = "filelock", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "filelock", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, { name = "fsspec", extra = ["http"], marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "jinja2", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "jinja2", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, { name = "networkx", version = "3.4.2", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux') or (python_full_version >= '3.11' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (python_full_version >= '3.11' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (python_full_version >= '3.11' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "networkx", version = "3.5", source = { registry = "https://pypi.org/simple" }, marker = "(python_full_version >= '3.11' and sys_platform != 'darwin' and sys_platform != 'linux') or (python_full_version < '3.11' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (python_full_version < '3.11' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (python_full_version < '3.11' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "setuptools", marker = "(python_full_version >= '3.12' and sys_platform != 'darwin' and sys_platform != 'linux') or (python_full_version < '3.12' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (python_full_version < '3.12' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (python_full_version < '3.12' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "sympy", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "triton", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "typing-extensions", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "setuptools", marker = "python_full_version >= '3.12' and sys_platform != 'darwin' and sys_platform != 'linux'" }, + { name = "sympy", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, + { name = "triton", marker = "sys_platform == 'never'" }, + { name = "typing-extensions", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, ] wheels = [ { url = "https://download.pytorch.org/whl/cu130/torch-2.9.0%2Bcu130-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:46004a346db6bfd69ecd2e42dce48e0fce2ad0e5a910f8203db5206f5515387e" }, @@ -9136,8 +9132,8 @@ version = "0.0.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "numpy" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "torchvision", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "torch", marker = "sys_platform == 'never'" }, + { name = "torchvision", marker = "sys_platform == 'never'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/6f/36/574c0c46e818533b78b3c09505211162918188325ab4165ef11a3f295755/torchprofile-0.0.4.tar.gz", hash = "sha256:96b6da17d752a06b02977e078aea95614893b31d4117dd5dcd081f30ce65611b", size = 4557, upload-time = "2021-06-22T04:58:03.592Z" } wheels = [ @@ -9165,9 +9161,9 @@ name = "torchvision" version = "0.24.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "numpy", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "pillow", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "numpy", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, + { name = "pillow", marker = "sys_platform != 'darwin' and sys_platform != 'linux'" }, + { name = "torch", marker = "sys_platform == 'never'" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/63/5b/1404eeab00819df71a30e916c2081654366741f7838fcc4fff86b7bd9e7e/torchvision-0.24.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5e8d5e667deff87bd66d26df6d225f46224bb0782d4f3f8f5d2f3068b5fd4492", size = 1891723, upload-time = "2025-10-15T15:51:08.5Z" }, @@ -9209,7 +9205,7 @@ name = "tqdm" version = "4.67.1" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/a8/4b/29b4ef32e036bb34e4ab51796dd745cdba7ed47ad142a9f4a1eb8e0c744d/tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2", size = 169737, upload-time = "2024-11-24T20:12:22.481Z" } wheels = [ @@ -9242,11 +9238,8 @@ wheels = [ ] [package.optional-dependencies] -core-cu13 = [ - { name = "transformer-engine-cu13", marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, -] pytorch = [ - { name = "transformer-engine-torch" }, + { name = "transformer-engine-torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, ] [[package]] @@ -9263,31 +9256,17 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/fa/a2/1439bbb6bc7d4d6045bad7d213884f7be92301c0982f009e3bbafa40e4ff/transformer_engine_cu12-2.11.0-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:6e5c0707583b2a90b2570da6f57409c6802653e069dfec38cf07a3b77ba9b12d", size = 288159349, upload-time = "2026-01-02T09:57:56.435Z" }, ] -[[package]] -name = "transformer-engine-cu13" -version = "2.12.0" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "importlib-metadata", marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "packaging", marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, - { name = "pydantic", marker = "sys_platform != 'darwin' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, -] -wheels = [ - { url = "https://files.pythonhosted.org/packages/01/b3/f9a4b6e7529dd138264be1ab6a4db3f5d436c31af591763eae09548972f0/transformer_engine_cu13-2.12.0-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:352c232de49d530ed3068987798f582f0b683ebe77f5b68ca01111663796501a", size = 189023259, upload-time = "2026-02-21T06:04:19.897Z" }, - { url = "https://files.pythonhosted.org/packages/a8/cb/e252e8cbbfa4dc856be79f914a75c0b78561b08273d489e1e397fc525fca/transformer_engine_cu13-2.12.0-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:cc63e1592ebebbd8ac000e4f5fb64e96a072c5a99d9850110b8d39dc9b7eeeca", size = 189804753, upload-time = "2026-02-21T06:04:23.07Z" }, -] - [[package]] name = "transformer-engine-torch" version = "2.12.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "einops" }, - { name = "nvdlfw-inspect" }, - { name = "onnx" }, - { name = "onnxscript" }, - { name = "packaging" }, - { name = "pydantic" }, + { name = "einops", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "nvdlfw-inspect", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "onnx", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "onnxscript", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "packaging", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "pydantic", marker = "(sys_platform != 'darwin' and sys_platform != 'linux') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'darwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'linux' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "torch", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, { name = "transformer-engine-cu12", marker = "sys_platform == 'never' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, ] @@ -9295,7 +9274,7 @@ sdist = { url = "https://files.pythonhosted.org/packages/b0/aa/5872f0944e88b9a7a [[package]] name = "transformers" -version = "5.3.0" +version = "5.2.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "huggingface-hub" }, @@ -9306,11 +9285,11 @@ dependencies = [ { name = "safetensors" }, { name = "tokenizers" }, { name = "tqdm" }, - { name = "typer" }, + { name = "typer-slim" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/fc/1a/70e830d53ecc96ce69cfa8de38f163712d2b43ac52fbd743f39f56025c31/transformers-5.3.0.tar.gz", hash = "sha256:009555b364029da9e2946d41f1c5de9f15e6b1df46b189b7293f33a161b9c557", size = 8830831, upload-time = "2026-03-04T17:41:46.119Z" } +sdist = { url = "https://files.pythonhosted.org/packages/bd/7e/8a0c57d562015e5b16c97c1f0b8e0e92ead2c7c20513225dc12c2043ba9f/transformers-5.2.0.tar.gz", hash = "sha256:0088b8b46ccc9eff1a1dca72b5d618a5ee3b1befc3e418c9512b35dea9f9a650", size = 8618176, upload-time = "2026-02-16T18:54:02.867Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/b8/88/ae8320064e32679a5429a2c9ebbc05c2bf32cefb6e076f9b07f6d685a9b4/transformers-5.3.0-py3-none-any.whl", hash = "sha256:50ac8c89c3c7033444fb3f9f53138096b997ebb70d4b5e50a2e810bf12d3d29a", size = 10661827, upload-time = "2026-03-04T17:41:42.722Z" }, + { url = "https://files.pythonhosted.org/packages/4e/93/79754b0ca486e556c2b95d4f5afc66aaf4b260694f3d6e1b51da2d036691/transformers-5.2.0-py3-none-any.whl", hash = "sha256:9ecaf243dc45bee11a7d93f8caf03746accc0cb069181bbf4ad8566c53e854b4", size = 10403304, upload-time = "2026-02-16T18:53:59.699Z" }, ] [[package]] @@ -9382,17 +9361,29 @@ wheels = [ [[package]] name = "typer" -version = "0.19.2" +version = "0.24.1" source = { registry = "https://pypi.org/simple" } dependencies = [ + { name = "annotated-doc" }, { name = "click" }, { name = "rich" }, { name = "shellingham" }, - { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/21/ca/950278884e2ca20547ff3eb109478c6baf6b8cf219318e6bc4f666fad8e8/typer-0.19.2.tar.gz", hash = "sha256:9ad824308ded0ad06cc716434705f691d4ee0bfd0fb081839d2e426860e7fdca", size = 104755, upload-time = "2025-09-23T09:47:48.256Z" } +sdist = { url = "https://files.pythonhosted.org/packages/f5/24/cb09efec5cc954f7f9b930bf8279447d24618bb6758d4f6adf2574c41780/typer-0.24.1.tar.gz", hash = "sha256:e39b4732d65fbdcde189ae76cf7cd48aeae72919dea1fdfc16593be016256b45", size = 118613, upload-time = "2026-02-21T16:54:40.609Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/00/22/35617eee79080a5d071d0f14ad698d325ee6b3bf824fc0467c03b30e7fa8/typer-0.19.2-py3-none-any.whl", hash = "sha256:755e7e19670ffad8283db353267cb81ef252f595aa6834a0d1ca9312d9326cb9", size = 46748, upload-time = "2025-09-23T09:47:46.777Z" }, + { url = "https://files.pythonhosted.org/packages/4a/91/48db081e7a63bb37284f9fbcefda7c44c277b18b0e13fbc36ea2335b71e6/typer-0.24.1-py3-none-any.whl", hash = "sha256:112c1f0ce578bfb4cab9ffdabc68f031416ebcc216536611ba21f04e9aa84c9e", size = 56085, upload-time = "2026-02-21T16:54:41.616Z" }, +] + +[[package]] +name = "typer-slim" +version = "0.24.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "typer" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/a7/a7/e6aecc4b4eb59598829a3b5076a93aff291b4fdaa2ded25efc4e1f4d219c/typer_slim-0.24.0.tar.gz", hash = "sha256:f0ed36127183f52ae6ced2ecb2521789995992c521a46083bfcdbb652d22ad34", size = 4776, upload-time = "2026-02-16T22:08:51.2Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a7/24/5480c20380dfd18cf33d14784096dca45a24eae6102e91d49a718d3b6855/typer_slim-0.24.0-py3-none-any.whl", hash = "sha256:d5d7ee1ee2834d5020c7c616ed5e0d0f29b9a4b1dd283bdebae198ec09778d0e", size = 3394, upload-time = "2026-02-16T22:08:49.92Z" }, ] [[package]] @@ -9454,7 +9445,7 @@ source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "click" }, { name = "h11" }, - { name = "typing-extensions", marker = "python_full_version < '3.11' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/71/57/1616c8274c3442d802621abf5deb230771c7a0fec9414cb6763900eb3868/uvicorn-0.37.0.tar.gz", hash = "sha256:4115c8add6d3fd536c8ee77f0e14a7fd2ebba939fed9b02583a97f80648f9e13", size = 80367, upload-time = "2025-09-23T13:33:47.486Z" } wheels = [ @@ -9463,11 +9454,11 @@ wheels = [ [package.optional-dependencies] standard = [ - { name = "colorama", marker = "sys_platform == 'win32' or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "colorama", marker = "sys_platform == 'win32'" }, { name = "httptools" }, { name = "python-dotenv" }, { name = "pyyaml" }, - { name = "uvloop", marker = "(platform_python_implementation != 'PyPy' and sys_platform != 'cygwin' and sys_platform != 'win32') or (platform_python_implementation == 'PyPy' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (platform_python_implementation == 'PyPy' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (platform_python_implementation == 'PyPy' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'cygwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'cygwin' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'cygwin' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'win32' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-trtllm') or (sys_platform == 'win32' and extra == 'extra-18-nemo-export-deploy-trt-onnx' and extra == 'extra-18-nemo-export-deploy-vllm') or (sys_platform == 'win32' and extra == 'extra-18-nemo-export-deploy-trtllm' and extra == 'extra-18-nemo-export-deploy-vllm')" }, + { name = "uvloop", marker = "platform_python_implementation != 'PyPy' and sys_platform != 'cygwin' and sys_platform != 'win32'" }, { name = "watchfiles" }, { name = "websockets" }, ]