Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[https://nvbugs/6130334][fix] Derive timeout from slurm.job_time when no explicit timeout exists, set iteratio
#13691
opened May 1, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] Add bf16 trtllm moe through flashinfer.
#13689
opened May 1, 2026 by
nv-guomingz
Collaborator
•
Draft
1 task done
[TRTLLM-12432][perf] ltx2: drop redundant pe all-gather in AV cross-attention
#13687
opened May 1, 2026 by
luyiyun1021
Collaborator
Loading…
1 task done
[https://nvbugs/6115832][fix] Fix SSE stream parsing in benchmark client to handle split chunks
#13686
opened May 1, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6082303][fix] Treat <tool_call> as implicit end-of-reasoning in nano-v3 parser
#13684
opened May 1, 2026 by
tijyojwad
Collaborator
Loading…
1 task done
[None][chore] KV Cache Transceiver Profiling Configs
#13681
opened Apr 30, 2026 by
ekou24
Collaborator
Loading…
1 task
[https://nvbugs/5911304][fix] Add URL validation for media input loading
#13680
opened Apr 30, 2026 by
yibinl-nvidia
Collaborator
Loading…
1 task done
[https://nvbugs/6109745][fix] Use ignore_eos=True to prevent empty outputs from EOS sensitivity, replace exact
#13678
opened Apr 30, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][fix] Fix GPT-OSS KV-aware router hashing
#13675
opened Apr 30, 2026 by
SimengLiu-nv
Collaborator
Loading…
1 task done
[https://nvbugs/6104831][test] Add reproducer for gen-side blocking hang in checkGenTransferStatus(at_least=1)
#13674
opened Apr 30, 2026 by
chienchunhung
Collaborator
•
Draft
1 task
[https://nvbugs/6104831][fix] Free recv buffer index on cancelled-after-ready disagg generation request
#13673
opened Apr 30, 2026 by
chienchunhung
Collaborator
•
Draft
1 task
[https://nvbugs/6104831][fix] Fulfill receiver future on disagg gen-side queued cancel
#13672
opened Apr 30, 2026 by
chienchunhung
Collaborator
•
Draft
1 task
[https://nvbugs/6104831][fix] Skip unready futures in checkGenTransferStatus(at_least=1)
#13671
opened Apr 30, 2026 by
chienchunhung
Collaborator
•
Draft
1 task
[https://nvbugs/6129630][fix] Removed all explicit imports from
mla/__init__.py (following the `attention/__
#13669
opened Apr 30, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6114464][fix] Add kv_cache_config to TestQwen3VL_MOE::test_auto_dtype
#13668
opened Apr 30, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][perf] Improve TRTLLM MoE autotune in DEP
#13667
opened Apr 30, 2026 by
rosenrodt
Collaborator
Loading…
1 task done
[#3324][fix] Honor tie_word_embeddings when sharing lm_head and embedding weights
Community want to contribute
PRs initiated from Community
#13664
opened Apr 30, 2026 by
javierdejesusda
Loading…
5 tasks done
[https://nvbugs/6115039][fix] Override
from_hf in Qwen3HybridConfig to pre-compute num_attention_layers
#13663
opened Apr 30, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
Disagg KV transfer hardening (rebased onto v1.3.0rc13)
Community want to contribute
PRs initiated from Community
[None][test] add Nemotron Ultra V3 AutoDeploy accuracy test
#13658
opened Apr 30, 2026 by
tcherckez-nvidia
Collaborator
Loading…
1 task done
[None][feat] Add more disagg conversation ID headers support
#13656
opened Apr 30, 2026 by
reasonsolo
Collaborator
Loading…
1 task done
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.