Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
346 Open 3,442 Closed
346 Open 3,442 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-6341][feature][kv cache manager] Support SWA KV cache reuse
#6768 opened Aug 10, 2025 by eopXD • Draft
9
[TRTLLM-6341][chore][kv cache manager] Preliminary refactors before supporting swa kv cahce reuse
#6767 opened Aug 10, 2025 by eopXD Loading…
4
[TRTLLM-7030][fix] Refactor the example doc of dist-serving
#6766 opened Aug 9, 2025 by Shixiaowei02 Loading…
20
[TRTLLM-5252][fix] Propagate mapping to intermediate layers (#6611)
#6765 opened Aug 9, 2025 by 2ez4bz Loading…
8
[None][test] Add accuracy evaluation for AutoDeploy Community want to contribute PRs initiated from Community
#6764 opened Aug 9, 2025 by ajrasane Loading…
2
[None][chore] Find LLM_ROOT and LLM_BACKEND_ROOT dynamically
#6763 opened Aug 8, 2025 by achartier Loading…
7
fix: Accommodate Phi3/4 to work with ModelOpt's FP8 ckpts in Torch
#6761 opened Aug 8, 2025 by moraxu Loading…
8
[#4403][autodeploy] Refactor: Move more transformations to new inf optimizer, Add quantization_source to factory interface
#6760 opened Aug 8, 2025 by Fridah-nv Loading…
52
[None][fix] Fix: Add missing va_end(args0) in fmtstr_ to prevent potential resource leak Community want to contribute PRs initiated from Community
#6758 opened Aug 8, 2025 by fyf2016 Loading…
3
[None][feat] Add single block version renormalized routing kernel
#6756 opened Aug 8, 2025 by ChristinaZ Loading…
@ChristinaZ
6
[None] [refactor] Reorganize CMake and Python integration test infrastructure for C++ tests
#6754 opened Aug 8, 2025 by Funatiq • Draft
5
[None][chore] Guided decoding fixes and benchmarking
#6752 opened Aug 8, 2025 by syuoni • Draft
7
[TRTLLM-6633][feat] Padding for piecewise cudagraph
#6750 opened Aug 8, 2025 by liji-nv • Draft
11
[TRTLLM-6975][test] Add multi-turn test cases for VLM models
#6749 opened Aug 8, 2025 by crazydemo Loading…
19
[None][chore] always try-catch when clear build folder in build_wheel.py
#6748 opened Aug 8, 2025 by zhenhuaw-me Loading…
@zhenhuaw-me
5
[TRTLLM-6768][infra] Fix params for not updating github status
#6747 opened Aug 8, 2025 by yiqingy0 Loading…
2
[None][fix] acceptance rate calculation fix in benchmark_serving
#6746 opened Aug 8, 2025 by zerollzeng Loading…
19
[TRTLLM-6906][chore] Using pybind to bind functions in thop/attentionOp Community want to contribute PRs initiated from Community
#6745 opened Aug 8, 2025 by lancelly Loading…
36
[https://nvbugs/5444624][fix] Fix LLM_ROOT in triton_backend build.sh
#6744 opened Aug 8, 2025 by yiqingy0 Loading…
15
[TRTLLM-5195][feat] Add standalone multimodal encoder (2/N)
#6743 opened Aug 8, 2025 by chang-l Loading…
88
[TRTLLM-6791][infra] Add check for upload stage name, to avoid override of test result tar
#6742 opened Aug 8, 2025 by ZhanruiSunCh Loading…
7
[TRTLLM-7014][chore] Add accuracy test for ctx and gen workers with different models
#6741 opened Aug 8, 2025 by reasonsolo Loading…
10
[None][doc] add blackwell information into support matrix 1.0_doc
#6740 opened Aug 8, 2025 by nv-guomingz Loading…
7
[None][test] Add perf-sweep scripts
#6738 opened Aug 8, 2025 by chenfeiz0326 Loading…
15
[https://nvbugs/5431127][fix] Run test_disaggregated_deepseek_v3_lite_fp8_nixl[DeepSeek-V3-Lite-fp8] only on hopper
#6737 opened Aug 8, 2025 by bo-nv Loading…
4
ProTip! no:milestone will show everything without a milestone.