Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][fix] Add support for context multiCtaKv sparse fmha
#13410
opened Apr 24, 2026 by
heyuhhh
Collaborator
Loading…
1 task done
[None][chore] Include layer_idx in MoE backend fallback warnings
#13409
opened Apr 24, 2026 by
dc3671
Collaborator
Loading…
2 tasks
[None][fix] Consolidate aiohttp session management in disagg router
#13408
opened Apr 24, 2026 by
reasonsolo
Collaborator
Loading…
1 task done
[https://nvbugs/6099723][fix] Moved qwen3_235b_a22b_fp8 ep:8 to the enable_attention_dp=False config group, an
#13407
opened Apr 24, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/5880745][test] GPT-OSS piecewise CUDA graph regression
#13406
opened Apr 24, 2026 by
crazydemo
Collaborator
Loading…
1 task done
[https://nvbugs/6102381][fix] serve /metrics from tee buffer to avoid racing iter stats collector
#13405
opened Apr 24, 2026 by
JunyiXu-nv
Collaborator
Loading…
1 task done
[TRTLLM-12200][feat] WideEP FT: add active_rank_mask to NVLink AlltoAll kernels (1a.2)
#13404
opened Apr 24, 2026 by
chienchunhung
Collaborator
•
Draft
1 task
[None][fix] AutoDeploy logger fix
#13403
opened Apr 24, 2026 by
suyoggupta
Collaborator
Loading…
2 tasks done
[https://nvbugs/6093714][fix] Replace test_auto_dtype[torch-True-1]
#13402
opened Apr 24, 2026 by
govind-ramnarayan
Collaborator
Loading…
1 task done
[None][test] add W4A8_MXFP4_FP8 MoE unit test support
#13401
opened Apr 24, 2026 by
xxi-nv
Collaborator
Loading…
1 task
[][] Submit disagg slurm task with kvbm
#13400
opened Apr 24, 2026 by
reasonsolo
Collaborator
•
Draft
1 task
[https://nvbugs/5997534][fix] Fix eagle3 accuracy test - attn backend must be flashinfer
#13398
opened Apr 23, 2026 by
govind-ramnarayan
Collaborator
Loading…
1 task done
[https://nvbugs/6080024][fix] Fix CudaGraphConfig validation conflict from YAML deep merge
#13397
opened Apr 23, 2026 by
nvchenghaoz
Collaborator
Loading…
1 task
[#13321][fix] disable multi_stream on piecewise path instead of persistent buffer
#13396
opened Apr 23, 2026 by
suyoggupta
Collaborator
Loading…
4 tasks
[None][doc] Fix stale --disable_xqa reference in legacy docs
Community want to contribute
PRs initiated from Community
#13395
opened Apr 23, 2026 by
Erfandarzi
Loading…
1 task
DRAFT proof: Kimi K2.5 + Eagle3 shadow-failover stack (do not merge)
Community want to contribute
PRs initiated from Community
#13394
opened Apr 23, 2026 by
galletas1712
•
Draft
[None][doc] Add blog post for tuning batch sizes for CUDA graph padding and increasing the default batch size granularity for it
#13393
opened Apr 23, 2026 by
yijingl-nvidia
Collaborator
Loading…
1 task done
[None][perf] add headsize 256 fmha for QWen3.6 on Spark
#13392
opened Apr 23, 2026 by
ttyio
Collaborator
Loading…
1 task
[https://nvbugs/6025330][fix] Use weights_only=True in LoRA manager torch.load
#13391
opened Apr 23, 2026 by
yibinl-nvidia
Collaborator
Loading…
1 task done
[None][fix] Enable MoE load balancer setup for Kimi-K2.5
#13386
opened Apr 23, 2026 by
qiaoxj07
Collaborator
Loading…
2 tasks done
[None][feat] Add duration-based execution to benchmark
Community want to contribute
PRs initiated from Community
#13385
opened Apr 23, 2026 by
weikuo0506
Loading…
[None][feat] Add MegaMoEFusedMoE backend wrapping DeepGEMM fp8_fp4_mega_moe
#13384
opened Apr 23, 2026 by
Barry-Delaney
Collaborator
•
Draft
1 task
[None][feat] Add W4A8_MXFP4_MXFP8 to DeepGemmFusedMoE
#13383
opened Apr 23, 2026 by
Barry-Delaney
Collaborator
•
Draft
1 task
[TRTLLM-12152][infra] Init Rule Based Change Based Test Selection
#13382
opened Apr 23, 2026 by
crazydemo
Collaborator
Loading…
1 task done
[None][chore] Update CI allowlist 2026-04-23
#13381
opened Apr 23, 2026 by
ZhanruiSunCh
Collaborator
Loading…
1 task
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.