Skip to content

Commit

Permalink
.
Browse files Browse the repository at this point in the history
  • Loading branch information
XiaotongJiang committed Dec 31, 2024
1 parent abffe6f commit 84ba180
Show file tree
Hide file tree
Showing 2 changed files with 43 additions and 47 deletions.
5 changes: 2 additions & 3 deletions .github/workflows/pr-test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ jobs:
unit-test-backend-1-gpu:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 2-gpu-runner
runs-on: 1-gpu-runner
strategy:
matrix:
range: [0-6, 6-16, 16-23, 23-30, 30-100]
Expand All @@ -62,10 +62,9 @@ jobs:
FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu124/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu124/torch2.4/flashinfer' }}
run: |
bash scripts/ci_install_dependency.sh
pip install --upgrade "evalplus[vllm] @ git+https://github.com/evalplus/evalplus"
- name: Run test
timeout-minutes: 120
timeout-minutes: 25
run: |
cd test/srt
RANGE=${{ matrix.range }}
Expand Down
85 changes: 41 additions & 44 deletions test/srt/run_suite.py
Original file line number Diff line number Diff line change
Expand Up @@ -5,53 +5,50 @@

suites = {
"per-commit": [
# "models/test_embedding_models.py",
# "models/test_generation_models.py",
# "models/test_lora.py",
# "models/test_reward_models.py",
# "sampling/penaltylib",
# "test_abort.py",
# "test_chunked_prefill.py",
# "test_double_sparsity.py",
# "test_embedding_openai_server.py",
# "test_eval_accuracy_mini.py",
# "test_get_weights_by_name.py",
# "test_gguf.py",
# "test_input_embeddings.py",
# "test_json_constrained.py",
# "test_large_max_new_tokens.py",
# "test_metrics.py",
# "test_no_chunked_prefill.py",
# "test_no_overlap_scheduler.py",
# "test_openai_server.py",
# "test_pytorch_sampling_backend.py",
# "test_radix_attention.py",
# "test_retract_decode.py",
# "test_server_args.py",
# "test_session_control.py",
# "test_skip_tokenizer_init.py",
# "test_srt_engine.py",
# "test_srt_endpoint.py",
# "test_torch_compile.py",
# "test_torch_compile_moe.py",
# # Temporarily disable this because it requires PyTorch >= 2.5
# # "test_torch_native_attention_backend.py",
# "test_torchao.py",
# "test_triton_attention_kernels.py",
# "test_triton_attention_backend.py",
# "test_update_weights_from_disk.py",
# "test_update_weights_from_tensor.py",
# "test_vision_chunked_prefill.py",
# "test_vision_openai_server.py",
# "test_session_control.py",
# "test_engine_token_ids.py",
"test_nightly_math_eval.py",
"test_nightly_human_eval.py",
"test_nightly_gsm8k_eval.py",
"models/test_embedding_models.py",
"models/test_generation_models.py",
"models/test_lora.py",
"models/test_reward_models.py",
"sampling/penaltylib",
"test_abort.py",
"test_chunked_prefill.py",
"test_double_sparsity.py",
"test_embedding_openai_server.py",
"test_eval_accuracy_mini.py",
"test_get_weights_by_name.py",
"test_gguf.py",
"test_input_embeddings.py",
"test_json_constrained.py",
"test_large_max_new_tokens.py",
"test_metrics.py",
"test_no_chunked_prefill.py",
"test_no_overlap_scheduler.py",
"test_openai_server.py",
"test_pytorch_sampling_backend.py",
"test_radix_attention.py",
"test_retract_decode.py",
"test_server_args.py",
"test_session_control.py",
"test_skip_tokenizer_init.py",
"test_srt_engine.py",
"test_srt_endpoint.py",
"test_torch_compile.py",
"test_torch_compile_moe.py",
# Temporarily disable this because it requires PyTorch >= 2.5
# "test_torch_native_attention_backend.py",
"test_torchao.py",
"test_triton_attention_kernels.py",
"test_triton_attention_backend.py",
"test_update_weights_from_disk.py",
"test_update_weights_from_tensor.py",
"test_vision_chunked_prefill.py",
"test_vision_openai_server.py",
"test_session_control.py",
"test_engine_token_ids.py",
],
"nightly": [
"test_nightly_gsm8k_eval.py",
"test_nightly_human_eval.py",
# "test_nightly_human_eval.py",
"test_nightly_math_eval.py",
],
"sampling/penaltylib": glob.glob(
Expand Down

0 comments on commit 84ba180

Please sign in to comment.