Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
237 Open 1,610 Closed
237 Open 1,610 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix: max_num_sequences calculation with overlap scheduling
#4532 opened May 21, 2025 by Funatiq • Draft
2
chore: clean ucx and nixl mirror.
#4531 opened May 21, 2025 by nv-guomingz Loading…
4
Qwen3 supports TRTLLM FP4 MoE backend
#4530 opened May 21, 2025 by rosenrodt Loading…
13
fix[nvbug/5286515]: trtllm-llmapi-launch on single node single gpu
#4529 opened May 21, 2025 by Superjomn Loading…
1
chore: minor refactoring and code clean-up
#4526 opened May 21, 2025 by Superjomn Loading…
feat: better build_wheel.py venv handling
#4525 opened May 21, 2025 by tongyuantongyu Loading…
11
[5180961] chore: Unwaive test for Qwen model.
#4524 opened May 21, 2025 by hyukn Loading…
8
[nvbugs5214239] - Unwaive test
#4523 opened May 21, 2025 by yiqingy0 Loading…
3
test: conditional disagg and cache aware balancing for deepseek v3
#4522 opened May 21, 2025 by zhengd-nv Loading…
5
fix: Constrain tornado and setuptools
#4521 opened May 21, 2025 by kaiyux Loading…
[5234029][5226211] chore: Unwaive multimodal tests for Qwen model.
#4519 opened May 21, 2025 by hyukn Loading…
7
User/nvpohanh/cherry pick llama4 change
#4518 opened May 21, 2025 by nvpohanh • Draft
[https://nvbugspro.nvidia.com/bug/5181262] [test] Unwaive Mistral Nemo test
#4515 opened May 21, 2025 by syuoni Loading…
3
feat: Skip sampler for intermediate pp stages.
#4514 opened May 21, 2025 by yuxianq Loading…
9
[fix] Fix Llama4 allgather error due to None tensor
#4511 opened May 21, 2025 by jinyangyuan-nvidia Loading…
@jinyangyuan-nvidia
15
test: rcca https://nvbugs/5223130
#4510 opened May 21, 2025 by xinhe-nv • Draft
[TRTLLM-5053] Refactoring and Unifying the Multimodal input preparation
#4506 opened May 21, 2025 by rakib-hasan Loading…
6
fix: TRT-LLM Gen dtype declaration
#4503 opened May 20, 2025 by nekorobov Loading…
6
Add UB NCCL integration
#4500 opened May 20, 2025 by Tabrizian • Draft
test(perf): Pt.2 Add Llama-3_3-Nemotron-Super-49B-v1 integration-perf-tests (cpp)
#4499 opened May 20, 2025 by venkywonka Loading…
6
fix: Handle additional model outputs based on pipeline parallel rank
#4498 opened May 20, 2025 by Funatiq Loading…
3
feat: forward exceptions to Python and catch OOMs
#4497 opened May 20, 2025 by ixlmar Loading…
4
[TRTLLM-4783][feat] Mamba2 kernel updates for Nemotron-H
#4494 opened May 20, 2025 by tomeras91 Loading…
12
Add debug nvtx
#4492 opened May 20, 2025 by Shunkangz • Draft
perf: [draft] Add fused q_norm/k_norm/RoPE for Qwen3.
#4482 opened May 20, 2025 by bobboli Loading…
3
ProTip! Filter pull requests by the default branch with base:main.