Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
407 Open 4,695 Closed
407 Open 4,695 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[None][chore] Add failed cases into waives.txt
#8284 opened Oct 11, 2025 by xinhe-nv • Draft
[None][infra] Add back gb200 multi-node test stage to pre-merge
#8281 opened Oct 11, 2025 by EmmaQiaoCh Loading…
1 task done
5
[None][chore] Upgrade transformers to 4.57.0.
#8280 opened Oct 11, 2025 by nv-guomingz Loading…
1 task done
10
[None][feat] Multi-LoRA serving with CUDA Graph
#8279 opened Oct 11, 2025 by JyChang012 Loading…
1 task
20
[None][chore] Migrate PluginConfig to Pydantic
#8277 opened Oct 11, 2025 by anish-shanbhag • Draft
1 task
[TRTLLM-7225][chore] Refactor model loading code for gptoss
#8276 opened Oct 10, 2025 by dongfengy • Draft
1 task
Enable CUDA graph support for KvConnectorWorker API Community want to contribute PRs initiated from Community
#8275 opened Oct 10, 2025 by nv-kmcgill53 Loading…
1 task
3
[https://nvbugs/5565530][fix] Unwaive test
#8273 opened Oct 10, 2025 by 2ez4bz Loading…
1 task done
5
[https://nvbugs/5522746][fix] unwaive tests caused by node issues after rebooting
#8268 opened Oct 10, 2025 by lancelly Loading…
4
[None][infra] Remove WAR code for GH200 node
#8267 opened Oct 10, 2025 by ZhanruiSunCh Loading…
1 task done
4
[None][infra] Remove WAR code for GH200 node
#8266 opened Oct 10, 2025 by ZhanruiSunCh Loading…
1 task done
4
[None][test] Add gpt_oss_20b Model to Sanity Perf Test
#8265 opened Oct 10, 2025 by yufeiwu-nv Loading…
1 task done
1
[TRTLLM-8532][chore] clean warmup method of ModelEngine
#8264 opened Oct 10, 2025 by QiJune Loading…
1 task done
10
[None][chore] update torch_dtype -> dtype in 'transformers'
#8263 opened Oct 10, 2025 by ixlmar • Draft
1 task done
3
[https://nvbugs/5546197][fix] Use local tokenizer
#8262 opened Oct 10, 2025 by LinPoly Loading…
1 task done
5
[None][feat] Add torch compile support for cuda core GEMM OP
#8261 opened Oct 10, 2025 by DylanChen-NV Loading…
1 task done
6
[None][fix] Fix EventLoopShutdownError
#8260 opened Oct 10, 2025 by dcaox Loading…
1 task done
7
[TRTLLM-8477][chore] Replace KvCacheConfigCpp with KvCacheConfig inside PyExecutor
#8259 opened Oct 10, 2025 by leslie-fang25 • Draft
1 task done
11
[https://nvbugs/5470769][chore] unwaive test for PR7338
#8258 opened Oct 10, 2025 by reasonsolo Loading…
1 task done
10
[https://nvbugs/5565590][fix] test_request_perf_metrics_draft
#8257 opened Oct 10, 2025 by Superjomn Loading…
1 task done
10
Support Glm4MoeForCausalLM Community want to contribute PRs initiated from Community
#8256 opened Oct 10, 2025 by dmtri35 Loading…
1 task
7
[https://nvbugs/5523315][fix] Fix serve benchmark test
#8255 opened Oct 10, 2025 by yechank-nvidia Loading…
@yechank-nvidia
4
[None][fix] add timeout for llama4
#8254 opened Oct 10, 2025 by xinhe-nv Loading…
1 task done
4
[https://nvbugs/5552132][fix] Enable LoRa for GPT OSS Torch
#8253 opened Oct 10, 2025 by moraxu • Draft
1 task
[https://nvbugs/5563653][infra] reduce docker image layers
#8250 opened Oct 10, 2025 by ZhanruiSunCh Loading…
1 task done
14
ProTip! Exclude everything labeled bug with -label:bug.