-
Notifications
You must be signed in to change notification settings - Fork 2k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[https://nvbugs/5769890][fix] Import get_free_port.
#10341
opened Dec 30, 2025 by
yuxianq
Loading…
1 task done
[None][feat] Run extra general warmup to warm up memory pool
#10340
opened Dec 30, 2025 by
liji-nv
Loading…
1 task done
[TRTLLM-9661][chore] Further reduce tuning time for cuteDSL nvFP4 dense gemm.
#10339
opened Dec 30, 2025 by
hyukn
Loading…
1 task done
[None][fix] disable thread leak check for kimi
#10337
opened Dec 30, 2025 by
xinhe-nv
Loading…
1 task done
[TRTLLM-10185][feat] AutoTuner Cache: Support cache file lock and merge all ranks into one
#10336
opened Dec 30, 2025 by
hyukn
Loading…
1 task done
[None][feat] WIP: Use XQA JIT impl by default
#10335
opened Dec 30, 2025 by
pengbowang-nv
•
Draft
1 task
[https://nvbugs/5707359][fix] Unwaive OOM case that should be fixed by #9446
#10334
opened Dec 30, 2025 by
liji-nv
Loading…
1 task done
[None][test] Unified slurm extra args management and session collection logic
#10332
opened Dec 30, 2025 by
fredricz-20070104
Loading…
[TRTLLM-10171][fix] Correct attention handling in ModelConfig and KVCacheManager
#10330
opened Dec 29, 2025 by
jaedeok-nvidia
Loading…
[#9656][feat] Load default sampling parameters (repetition_penalty, temperature, top_p, top_k and min_p) from generation_config.json
Community want to contribute
PRs initiated from Community
#10329
opened Dec 29, 2025 by
riZZZhik
Loading…
1 task done
[None][fix] impl fused triton kernel for e8m0 resmooth to reduce memory footprint
Community want to contribute
PRs initiated from Community
#10327
opened Dec 29, 2025 by
Nekofish-L
Loading…
1 task done
docs: clarify LoRA is not supported with --use_fp8_rowwise in Fp8RowwiseAttention (see #2603)
Community want to contribute
PRs initiated from Community
#10320
opened Dec 28, 2025 by
ssam18
Loading…
[TRTLLM-10318][feat] Fixing Nemotron sharding: support for sharding buffers
#10319
opened Dec 28, 2025 by
greg-kwasniewski1
Loading…
1 task done
Test: Add unit tests for path safety and edge cases
Community want to contribute
PRs initiated from Community
#10315
opened Dec 28, 2025 by
aryansri05
Loading…
[TRTLLM-9467][fix] Fix PP+CP combination with helix parallelism
#10312
opened Dec 27, 2025 by
brb-nv
Loading…
1 task done
[#10056][chore] AutoDeploy: Enable Nemo SuperV3 accuracy test
#10308
opened Dec 26, 2025 by
galagam
Loading…
1 task done
POC/aether sparse attention
Community want to contribute
PRs initiated from Community
#10305
opened Dec 26, 2025 by
teerthsharma
Loading…
[None] Add export data to build and run script for AD
#10299
opened Dec 25, 2025 by
tcherckez-nvidia
Loading…
1 task done
[TRTLLM-9707][infra] Support abort stage also upload results.xml to artifactory to support reuse test
#10297
opened Dec 25, 2025 by
ZhanruiSunCh
Loading…
1 task done
[#9717][chore] Standardize MoE weights interface
#10295
opened Dec 25, 2025 by
tcherckez-nvidia
Loading…
1 task done
[None][chore] fix empty tensor view issue
#10292
opened Dec 25, 2025 by
leslie-fang25
•
Draft
1 task done
Previous Next
ProTip!
Follow long discussions with comments:>50.