Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
241 Open 1,887 Closed
241 Open 1,887 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

fix: fix cuda graph padding for spec decoding
#4853 opened Jun 3, 2025 by lfr-0531 Loading…
2
Remove unnecessary duplicated tests from pre-merge H100 DGX
#4852 opened Jun 3, 2025 by litaotju Loading…
Replace memset with data initialization within kernels
#4851 opened Jun 3, 2025 by ChristinaZ Loading…
@ChristinaZ
enh: Enable trtllm-bench to run LoRA PyT flow
#4848 opened Jun 3, 2025 by venkywonka Loading…
4 of 5 tasks
@venkywonka
8
[DO NOT MERGE] test PR to test action
#4847 opened Jun 2, 2025 by poweiw • Draft
[Doc] Fix readme for disaggregated serving
#4846 opened Jun 2, 2025 by arekay Loading…
6
[nvbug 5283506] fix: Fix spec decode triton test
#4845 opened Jun 2, 2025 by pcastonguay Loading…
5
[nvbug/5314469][feat] Include the executor's max batch size in CUDA g…
#4843 opened Jun 2, 2025 by mikeiovine Loading…
7
Update code owner list
#4839 opened Jun 2, 2025 by juney-nvidia Loading…
3
Chore: refine prepre inputs method of model engine
#4837 opened Jun 2, 2025 by QiJune Loading…
6
Draft: feat: trtllm sampler log probs
#4836 opened Jun 2, 2025 by dcampora Loading…
Fix: NVBug 5302895
#4835 opened Jun 2, 2025 by Shixiaowei02 Loading…
5
test
#4831 opened Jun 2, 2025 by yunruis Loading…
1
fix: [nvbugs/5298600] fix illegal memory access on mrope_position_deltas
#4830 opened Jun 2, 2025 by yechank-nvidia Loading…
@yechank-nvidia
3
feat: port MakeDecodingBatchInputOutput to python in TRTLLMSampler
#4828 opened Jun 2, 2025 by dcampora Loading…
6
Fix trtllm-bench iter_stats and cuda_graph_batch_sizes error errors.
#4827 opened Jun 2, 2025 by qiaoxj07 Loading…
9
chore: memoize weight shuffle index to speed up weight preproc in moe_backend=TRTLLM
#4826 opened Jun 2, 2025 by rosenrodt Loading…
11
fix: make scale_bmm2_d optional in epilogue too
#4823 opened Jun 1, 2025 by hypdeb Loading…
[TRTLLM-4923][feat] Paged mamba cache
#4822 opened Jun 1, 2025 by tomeras91 Loading…
10
Draft: test: [CI] remove closed bugs
#4821 opened Jun 1, 2025 by xinhe-nv • Draft
[TRTLLM-4987][feat] Support generation logits in TRTLLMSampler
#4819 opened Jun 1, 2025 by amitz-nv Loading…
7
feat: large-scale EP(part 6: Online EP load balancer integration for GB200 nvfp4)
#4818 opened Jun 1, 2025 by dongxuy04 Loading…
42
[Arch] Freeze model_config
#4814 opened May 31, 2025 by hlu1 Loading…
17
feat: enable streaming weight updates
#4813 opened May 30, 2025 by hchings • Draft
3 tasks
@hchings
[enhanchment] Add beam width to low latency.
#4812 opened May 30, 2025 by FrankD412 Loading…
@FrankD412
4
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.