Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
201 Open 1,100 Closed
201 Open 1,100 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

pick Boyang's change to fix multi streams
#3880 opened Apr 26, 2025 by litaotju Loading…
4
fix: Set num_microbatches=pp_size with overlap scheduler
#3878 opened Apr 26, 2025 by amukkara Loading…
5
fix: [https://nvbugspro.nvidia.com/bug/5242406][fix] Fix fp8 kvcache support
#3877 opened Apr 26, 2025 by hlu1 Loading…
5
feat: Re-enable Llama4 fusion and add AllReduce CUDA Graph Fix
#3876 opened Apr 25, 2025 by zihaok Loading…
Draft: perf: [TRTLLM-4717][perf] Set CUDA graph max batch size and padding in throughput benchmark.
#3875 opened Apr 25, 2025 by FrankD412 Loading…
feat: Add py_state member in LlmRequest class
#3872 opened Apr 25, 2025 by QiJune Loading…
12
fix: [nvbugs/5066257] serialization improvments
#3869 opened Apr 25, 2025 by coldwaterq Loading…
6
Draft: test: [CI] Add failed cases into waives.txt
#3867 opened Apr 25, 2025 by xinhe-nv • Draft
feat: refactoring dataset generation and adding tests others
#3866 opened Apr 25, 2025 by hypdeb Loading…
@hypdeb
28
feat: add relaxed acceptance for DS
#3865 opened Apr 25, 2025 by yweng0828 Loading…
11
tests: skip writing prepare_dataset output to logs
#3864 opened Apr 25, 2025 by ruodil Loading…
@ruodil
fix: Fix FMHA-based MLA in the generation phase and add MLA unit test
#3863 opened Apr 25, 2025 by jinyangyuan-nvidia Loading…
@jinyangyuan-nvidia
6
fix: [https://nvbugspro.nvidia.com/bug/5243482] If FlashMLA is used, the existence of FMHA based MLA kernels should not be checked.
#3862 opened Apr 25, 2025 by bobboli Loading…
1
fix: fix bug of deepseek gropu_size setting
#3860 opened Apr 25, 2025 by byshiue Loading…
6
infra: [TRTLLM-4475][TRTLLM-4565] Add pipeline hierarchy and basic info in the Jenkins job page
#3859 opened Apr 25, 2025 by ZhanruiSunCh • Draft
@ZhanruiSunCh
1
fix: Detect pmix and raise error when mpirun is not used.
#3858 opened Apr 25, 2025 by yuxianq Loading…
14
feat: add health_generate route to openai serving Community Engagement Community want to contribute
#3856 opened Apr 25, 2025 by dsingal0 Loading…
1
feat: Add multimodal embedding field in LlmRequest
#3855 opened Apr 25, 2025 by katec846 Loading…
21
feat: enable PP on Llama4
#3854 opened Apr 25, 2025 by v-shobhit Loading…
fix: add warmup flag into py_executor to prevent enable profiler during wa…
#3852 opened Apr 25, 2025 by byshiue Loading…
4
feat:Low Precision Allreduce for PCIe based GPU
#3851 opened Apr 25, 2025 by kanghui0204 Loading…
14
chore: [DEMONSTRATION ONLY] 1st Mass integration of release/0.19
#3850 opened Apr 25, 2025 by tongyuantongyu • Draft
feat: AutoDeploy fp8 quantization support for bmm
#3849 opened Apr 25, 2025 by meenchen Loading…
@meenchen
feat: Mistral-Large-2 support in the Pytorch workflow LLM API/Workflow new model
#3845 opened Apr 24, 2025 by hypdeb Loading…
@hypdeb
22
temp
#3844 opened Apr 24, 2025 by netanel-haber • Draft
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.