Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
268 Open 2,326 Closed
268 Open 2,326 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

[doc] update mtp documents
#5387 opened Jun 20, 2025 by lfr-0531 Loading…
feat: Remove not used padding_idx in models
#5385 opened Jun 20, 2025 by HuiGao-NV Loading…
3
refactor: remove batch_manager::KvCacheConfig and use executor::KvCacheConfig instead
#5384 opened Jun 20, 2025 by Funatiq • Draft
6
Detokenize option in /v1/completions request Community Engagement help/insights needed from community Community want to contribute PRs initiated from Community
#5382 opened Jun 20, 2025 by Wokzy Loading…
Fix: missing clientId when serialize and deserialize response (cherry-pick #5231)
#5378 opened Jun 20, 2025 by kaiyux Loading…
3
[TRTLLM-5831][feat] Add LoRA support for pytorch backend in trtllm-serve
#5376 opened Jun 19, 2025 by talorabr Loading…
chore: Add scripts to profile cutlass moe
#5375 opened Jun 19, 2025 by bobboli • Draft
Fix permission for local user issues in NGC docker container.
#5373 opened Jun 19, 2025 by MartinMarciniszyn Loading…
@MartinMarciniszyn
3
Feat/unify checkpoints loading
#5372 opened Jun 19, 2025 by shaharmor98 • Draft
[TRTLLM-5838][fix] fix max batch size and max tokens in kv cache estimations for Nemotron-H
#5371 opened Jun 19, 2025 by tomeras91 Loading…
14
fix: fix bug of qwen3 + eagle3 + finalize_moe_fusion
#5369 opened Jun 19, 2025 by byshiue Loading…
3
Mxfp4 moe
#5367 opened Jun 19, 2025 by Tracin Loading…
tests: update benchmark test lists
#5365 opened Jun 19, 2025 by xinhe-nv Loading…
4
feat: TRTLLM-5941 Upgrade xgrammar to 0.1.18
#5364 opened Jun 19, 2025 by Wanli-Jiang • Draft
7
Make moe permute and final as custom op
#5358 opened Jun 19, 2025 by limin2021 Loading…
1
fix: Fix skip by mpi size fixture
#5355 opened Jun 19, 2025 by yizhang-nv Loading…
10
feat(openai protocol):support logitbias
#5354 opened Jun 19, 2025 by xq25478 Loading…
feat(eagle):support qwen in eagle1/2
#5352 opened Jun 19, 2025 by xq25478 Loading…
feat(model):support qwen3 dense in trt flow
#5350 opened Jun 19, 2025 by xq25478 Loading…
1
test: Add LLGuidance test and refine guided decoding
#5348 opened Jun 19, 2025 by syuoni Loading…
@syuoni
20
[TRTLLM-5350] Add Phi-4-Mini-Instruct in Pytorch backend for LLM API accuracy tests
#5347 opened Jun 19, 2025 by moraxu • Draft
feat: add LLmArgs option to force using dynamic quantization
#5346 opened Jun 19, 2025 by achartier Loading…
3
feat(scaffolding): add streaming scaffolding_llm.generate_async support
#5345 opened Jun 19, 2025 by dc3671 • Draft
[fix] Add 1 and draft_token_num to seq_len when overlap scheduling is enabled during memory estimation
#5343 opened Jun 19, 2025 by HuiGao-NV Loading…
16
[fix][test] parametrize deepseek eval
#5341 opened Jun 18, 2025 by omera-nv Loading…
27
ProTip! Updated in the last three days: updated:>2025-06-17.