Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[https://nvbugs/6076767][fix] [TensorRT-LLM][release/1.2.1]: accuracy/test_llm_a
#13132
opened Apr 16, 2026 by
ziyixiong-nv
Collaborator
Loading…
2 tasks done
[https://nvbugs/6035425][fix] Fix host memory usage regression with spec dec
#13130
opened Apr 16, 2026 by
mikeiovine
Collaborator
Loading…
1 task done
[https://nvbugs/6018172][fix] Fix DSA illegal memory access with CUDA graph and host KV cache offload
#13124
opened Apr 16, 2026 by
liji-nv
Collaborator
Loading…
1 task done
[None][fix] Disable multi stream moe for super v3
#13122
opened Apr 16, 2026 by
tcherckez-nvidia
Collaborator
Loading…
1 task done
[None][bug] fix SM90 full-mask skip-softmax dispatch
#13120
opened Apr 16, 2026 by
bobboli
Collaborator
Loading…
[TRTLLM-11123][fix] Propagate real errors to disagg server
#13119
opened Apr 16, 2026 by
reasonsolo
Collaborator
Loading…
1 task done
[https://nvbugs/5819019][fix] Remove waivers
#13118
opened Apr 16, 2026 by
YihuiLu512
Collaborator
Loading…
1 task done
[None][feat] Add FP4 residual quantization kernel without channel reo…
#13117
opened Apr 16, 2026 by
Tracin
Collaborator
Loading…
1 task done
[TRTLLM-10288][perf] Reduce AutoTuner host overhead in inference hot path
#13116
opened Apr 16, 2026 by
hyukn
Collaborator
Loading…
1 task done
[TRTLLM-12015][feat] Introduce KV reuse in transceiver v2
#13115
opened Apr 16, 2026 by
Shixiaowei02
Collaborator
•
Draft
1 task
fix: guard enable_partial_reuse_for_disagg against in-flight KV transfers
Community want to contribute
PRs initiated from Community
#13114
opened Apr 16, 2026 by
yifjiang
Contributor
Loading…
3 of 4 tasks
[None][infra] Waive 4 failed cases for main in post-merge 2654
#13113
opened Apr 16, 2026 by
ZhanruiSunCh
Collaborator
Loading…
[TRTLLM-11946][feat] Disaggregated gen-first serving with ADP
#13112
opened Apr 16, 2026 by
reasonsolo
Collaborator
Loading…
1 task done
[https://nvbugs/6018043][fix] Unwaive testcase
#13111
opened Apr 16, 2026 by
YihuiLu512
Collaborator
Loading…
1 task done
[None][chore] Add CODEOWNERS mappings for @NVIDIA/trt-llm-multimodal-devs
#13110
opened Apr 16, 2026 by
venkywonka
Collaborator
Loading…
[None][fix] Enforce NCCL >= 2.28 at CMake configure time
#13108
opened Apr 16, 2026 by
eopXD
Collaborator
Loading…
1 task done
[None][infra] Waive 2 failed cases for main in post-merge
#13105
opened Apr 16, 2026 by
xinhe-nv
Collaborator
Loading…
[None][fix] Fix errors in KV cache manager V2 and scheduler V2
#13104
opened Apr 16, 2026 by
jiaganc
Collaborator
Loading…
1 task done
[None][feat] Optimize causal_conv1d prefill and decode kernels
#13103
opened Apr 16, 2026 by
Wanli-Jiang
Collaborator
•
Draft
1 task done
[None][feat] Finetune three skills
#13101
opened Apr 16, 2026 by
jieli-matrix
Collaborator
Loading…
1 task done
[None][infra] Reenable GB300-4_GPUs-PyTorch-Post-Merge-1
#13097
opened Apr 16, 2026 by
mlefeb01
Collaborator
Loading…
1 task done
[None][pref] Consolidate prefix reuse queries into single analyzePrefixReuse radix tree walk
#13095
opened Apr 15, 2026 by
SimengLiu-nv
Collaborator
Loading…
1 task done
[https://nvbugs/6059036][fix] Fix AutoDeploy max_batch_size vs cuda_graph_config validation mismatch
#13093
opened Apr 15, 2026 by
marinayanov
Collaborator
Loading…
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.