Pull requests: NVIDIA/TensorRT-LLM
Author
Filter by author
Label
Filter by label
Loading
Projects
Milestones
Reviews
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Filter by reviews
Assignee
Filter by who’s assigned
Sort
Sort by
Pull requests list
[None][fix] Fix Qwen3.8-27B NVFP4 checkpoint loading
#18387
opened Aug 28, 2026 by
jupiterepoch
Loading…
1 task done
[https://nvbugs/6655990][test] Raise WAN multi-GPU LPIPS threshold to 0.32 and unwaive
VisualGen
#18386
opened Aug 28, 2026 by
chang-l
Collaborator
Loading…
1 task done
[https://nvbugs/6655986][test] Raise LTX-2 LPIPS golden thresholds to 0.15 and unwaive
VisualGen
#18384
opened Aug 28, 2026 by
chang-l
Collaborator
Loading…
1 task done
[TRTLLM-14575][perf] Use native next_n for DSA paged-MQA on Blackwell
#18383
opened Aug 28, 2026 by
xwang233
Collaborator
Loading…
1 task done
[https://nvbugs/6656598][fix] Fix Kimi-K2 E2E test
#18382
opened Aug 28, 2026 by
2ez4bz
Collaborator
Loading…
1 task done
[None][feat] Support image input in the Triton llmapi backend
#18381
opened Aug 28, 2026 by
faradawn
Collaborator
Loading…
[None][doc] Fix broken links across example and test READMEs
#18379
opened Aug 28, 2026 by
jlonge4
Loading…
1 task done
[None][doc] Fix broken Dynamo TensorRT LLM deployment link in DeepSeek-V3 README
#18378
opened Aug 28, 2026 by
jlonge4
Loading…
1 task done
[TRTLLM-15160][feat] Add post-attention o_proj gate hook to shared MLA base and make trtllm::kda_decode inplace-only
#18375
opened Aug 28, 2026 by
WeiHaocheng
Collaborator
Loading…
[https://nvbugs/6668807][fix] Remove invalid GLM KV cache assertion
#18374
opened Aug 28, 2026 by
yizhang-nv
Member
Loading…
1 task done
[https://nvbugs/6657468][fix] Set UCX_TLS for GB300 in disagg logprobs test
#18373
opened Aug 28, 2026 by
moraxu
Collaborator
Loading…
1 task done
[https://nvbugs/6681216][fix] Raise disagg nixl readiness timeout on Blackwell
ci: full pre-merge approved
#18372
opened Aug 28, 2026 by
brnguyen2
Collaborator
Loading…
4 tasks done
[TRTLLM-15820][feat] Enable Nemotron Super 3.5 VL video input
#18370
opened Aug 28, 2026 by
eopXD
Collaborator
Loading…
1 task done
[None][feat] Add Rubin SM107 CuTe DSL foundation and BF16 kernels
#18369
opened Aug 28, 2026 by
farazkh80
Collaborator
Loading…
1 task done
[https://nvbugs/6650388][fix] Flip the existing per-worker workspace isolation from opt-in to on-by-default…
#18368
opened Aug 28, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[None][feat] Allow restricting torch.compile to piecewise graph capture only
#18366
opened Aug 28, 2026 by
AlessioNetti
Collaborator
•
Draft
1 task
[https://nvbugs/6655986][fix] Gate the unquantized epilogue on TRTLLM_MLP_FUSE_GELU_EPILOGUE=1 (default…
#18365
opened Aug 28, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[https://nvbugs/6642218][fix] Preserve perf UCX settings across MPI launcher
#18364
opened Aug 28, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[None][infra] Add GB300 multi-node post-merge stages for Qwen3.8-2.4T-A95B NVFP4 accuracy
#18363
opened Aug 28, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[None][test] add a minimum-resource "basic" disagg smoke tier
#18360
opened Aug 28, 2026 by
fredricz-20070104
Collaborator
Loading…
[None][fix] Track request identity for DSA GVR top-k prior rows
#18359
opened Aug 28, 2026 by
longcheng-nv
Collaborator
•
Draft
[None][feat] add CuteDslFc12FusedMoE fused FC1+FC2 NVFP4 MoE backend (Rubin/SM107)
#18357
opened Aug 28, 2026 by
leslie-fang25
Collaborator
•
Draft
1 task done
[https://nvbugs/6669902][fix] Pass block_table.cpu().to(torch.int32) to the 3-arg helper in all three…
#18356
opened Aug 28, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
ProTip!
Adding no:label will show everything without a label.