Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
319 Open 2,595 Closed
319 Open 2,595 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

[TRTLLM-5881] feat: Integrate TRT-LLM Gen FP4 block scale MoE with Pytorch workflow kernel autotuner
#5764 opened Jul 4, 2025 by DomBrown • Draft
@DomBrown
Fix docker cache mount
#5763 opened Jul 4, 2025 by MartinMarciniszyn Loading…
@MartinMarciniszyn
4
[nvbugs/5369799] fix: Update disaggregation handling in sampler
#5762 opened Jul 4, 2025 by stnie • Draft
3
[nvbugs/5345391] fix: chunked prefill + overlap scheduling
#5761 opened Jul 4, 2025 by Funatiq • Draft
6
Add wide-ep benchmarking scripts
#5760 opened Jul 4, 2025 by qiaoxj07 Loading…
19
Fix --image_path param error in multimodal run.py tests Community want to contribute PRs initiated from Community
#5757 opened Jul 4, 2025 by pandalee99 Loading…
[Infra] - Always use x86 image for the Jenkins agent
#5756 opened Jul 4, 2025 by chzblych Loading…
6
Fix cancel request bug in attentiondp
#5754 opened Jul 4, 2025 by Shunkangz Loading…
@Shunkangz
3
[Infra] - Always use x86 image for the Jenkins agent and few clean-ups
#5753 opened Jul 4, 2025 by chzblych Loading…
12
[TRTLLM-5530][BREAKING CHANGE] refactor: unify KvCacheConfig in LLM class for pytorch backend
#5752 opened Jul 4, 2025 by Superjomn Loading…
3
[TRTLLM-5530][BREAKING CHANGE] refactor: LLM arglist rename mixed_sampler to enable_mixed_sampler
#5751 opened Jul 4, 2025 by Superjomn Loading…
3
chore: log stack trace on error in openai server
#5749 opened Jul 4, 2025 by zhengd-nv Loading…
6
Update transformers to 4.53.0
#5747 opened Jul 4, 2025 by Wanli-Jiang Loading…
13
[nvbug5266240] chore: unwaive test_llm_with_dummy_weights
#5744 opened Jul 4, 2025 by Superjomn Loading…
6
[feat] Adds optional module cache for TRT-LLM Gen Gemm interfaces
#5743 opened Jul 4, 2025 by davidclark-nv Loading…
3
feat: moe prepare support topk % 4 != 0
#5742 opened Jul 4, 2025 by WeiHaocheng Loading…
@WeiHaocheng
1
[feat] Support nvidia/Cosmos-Reason1-7B
#5739 opened Jul 4, 2025 by meatybobby Loading…
Custom attention mask in TRTLLM attention backend
#5738 opened Jul 4, 2025 by brb-nv • Draft
chores: merge examples for v1.0 doc
#5736 opened Jul 3, 2025 by hchings • Draft
1 of 3 tasks
@hchings
2
[TRTLLM-6070] docs: Add initial documentation for trtllm-bench CLI.
#5734 opened Jul 3, 2025 by FrankD412 Loading…
@FrankD412
[TRTLLM-5847][feat] Support n-gram speculative decoding with disagg
#5732 opened Jul 3, 2025 by raayandhar Loading…
7
chore: some refactor on WideEP
#5727 opened Jul 3, 2025 by dongxuy04 Loading…
18
[ci] speedup fused moe tests
#5726 opened Jul 3, 2025 by omera-nv Loading…
16
[mock] Testing the auto-assign PR functionality
#5725 opened Jul 3, 2025 by venkywonka • Draft
5
[feat] [https://nvbugs/5369010] Add TRTLLM MoE nvfp4 cubins for mid-high concurrency
#5723 opened Jul 3, 2025 by rosenrodt Loading…
7
ProTip! Type g i on any issue or pull request to go back to the issue listing page.