Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[#17126][fix] Align FP8 block-scales Python gates with C++ SM121 aliasing
#17166
opened Aug 1, 2026 by
DhineshPonnarasan
Contributor
•
Draft
[TRTLLM-14904][fix] Work around flashinfer 0.6.15 autotuner cache-key hash/eq inconsistency
#17165
opened Aug 1, 2026 by
brnguyen2
Collaborator
Loading…
3 tasks done
[None][fix] Drain in-flight requests before clearing the KV cache reuse state
#17163
opened Aug 1, 2026 by
lowsfer
Member
Loading…
1 task done
[TRTLLM-14903][fix] Free partially-allocated warmup dummy KV blocks and count spec extra tokens in warmup block estimates
#17162
opened Aug 1, 2026 by
brnguyen2
Collaborator
Loading…
2 tasks done
[TRTLLM-14772][doc] Add sudo to apt prerequisites
#17161
opened Aug 1, 2026 by
bobboli
Collaborator
Loading…
1 task done
[https://nvbugs/6463987][fix] Pin NCCL to 2.29.7 for GB300 GLM-5-NVFP4 perf
#17160
opened Aug 1, 2026 by
chenfeiz0326
Collaborator
Loading…
3 of 5 tasks
[#17158][fix] Reject NaN top_p, min_p and temperature in SamplingParams
#17159
opened Aug 1, 2026 by
Yigtwxx
Loading…
1 task done
[#17156][fix] Flush buffered text in DeepSeekR1Parser.finish()
#17157
opened Aug 1, 2026 by
Yigtwxx
Loading…
1 task done
[https://nvbugs/6428094][chore] Unwaive DeepSeekV3Lite tp2pp2 test
#17155
opened Aug 1, 2026 by
cascade812
Collaborator
Loading…
1 task done
[https://nvbugs/6535874][fix] Size DFlash/DSpark worker slot buffers from num_seq_slots
#17154
opened Aug 1, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[https://nvbugs/6517834][fix] Fix attn_dense LoRA input dim and Triton MoE padded-view output
#17153
opened Aug 1, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[https://nvbugs/6539941][fix] Preserve primary warmup error when batch cleanup also fails
#17152
opened Aug 1, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[#17146][fix] Fix Laguna's reasoning parser
#17151
opened Aug 1, 2026 by
1MrazorT1
Contributor
Loading…
1 task done
[https://nvbugs/6541322][fix] Remove stale waiver for TestQwen3NextInstruct::test_bf16_4gpu[dep4]
#17150
opened Aug 1, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[None][fix] Mark prototype status for API flag index_share_for_mtp_iteration
api-compatible
Accepted LLM API contract change that is backwards-compatible
#17149
opened Aug 1, 2026 by
nvxuanyuc
Collaborator
Loading…
[None][feat] Add Qwen Image Edit Ulysses support
VisualGen
#17147
opened Jul 31, 2026 by
yibinl-nvidia
Collaborator
•
Draft
1 task
[https://nvbugs/6535767][fix] Added an anonymous-namespace
childTokensPerBlock(NodeBase const&) deriving…
#17145
opened Jul 31, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[TRTLLM-14880][feat] qualify Qwen3 dense for MX
#17142
opened Jul 31, 2026 by
chienchunhung
Collaborator
•
Draft
1 task done
[NVBUG-6448152][test] replay pre-PR15356 native admission
#17141
opened Jul 31, 2026 by
chienchunhung
Collaborator
•
Draft
[None][fix] Bound GEN log sentinel wait
#17140
opened Jul 31, 2026 by
chienchunhung
Collaborator
Loading…
[NVBUG-6448152][test] compare rebased PR16645 throughput with main
api-compatible
Accepted LLM API contract change that is backwards-compatible
#17139
opened Jul 31, 2026 by
chienchunhung
Collaborator
•
Draft
[https://nvbugs/6265490][fix] Defer LoRA path validation
VisualGen
#17138
opened Jul 31, 2026 by
yibinl-nvidia
Collaborator
Loading…
1 task done
[https://nvbugs/6480621][test] Revert to 60-second KV transfer timeout for GB300 DeepSeek V4 Pro disaggregated perf-sanity
#17137
opened Jul 31, 2026 by
chienchunhung
Collaborator
•
Draft
[TRTLLMINF-237][infra] Adopt resourceLedger.withResource for BuildDockerImage
#17136
opened Jul 31, 2026 by
dpitman-nvda
Collaborator
Loading…
1 task done
[https://nvbugs/6525059][fix] Drop
8 from FP8BlockScaleMoeRunner::mSupportedTileN, covering both the…
#17135
opened Jul 31, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.