Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][test] Waive TestGemma4MoE::test_bf16 (missing bf16 MMMU reference)
#16289
opened Jul 12, 2026 by
dongfengy
Collaborator
Loading…
1 task done
[None][feat] Reuse freshly out-of-window SWA pages for new decode blocks in KV cache manager v2
#16288
opened Jul 12, 2026 by
lishicheng1996-nv
Collaborator
Loading…
1 task done
[None][fix] Clamp very small non-zero temperature in SamplingParams
#16287
opened Jul 12, 2026 by
CodersAcademy006
Contributor
Loading…
3 tasks done
[https://nvbugs/6412108][fix] Shard shared Qwen3.5 experts
bug
Something isn't working
#16286
opened Jul 12, 2026 by
greg-kwasniewski1
Collaborator
Loading…
4 tasks done
[https://nvbugs/6367792][fix] unwaive Nano AutoDeploy tests
#16285
opened Jul 12, 2026 by
tcherckez-nvidia
Collaborator
Loading…
1 task done
[None][test] Waive 1 failed cases for main in QA CI
#16283
opened Jul 12, 2026 by
trtllm-agent
Collaborator
•
Draft
[https://nvbugs/6432832][fix] After the tokenize await, reconcile the local
servers list under self._lock…
#16282
opened Jul 12, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[None][fix] Add seq-slot pool overlap headroom for V2 scheduler and guard ADP dummy insertion
#16279
opened Jul 11, 2026 by
qiaoxj07
Collaborator
Loading…
[#16196][fix] Support MIXED_PRECISION experts-only NVFP4 DeepSeek-V4 checkpoints
#16276
opened Jul 11, 2026 by
waynehacking8
Loading…
3 tasks done
[None][test] Waive 10 failed cases for main in QA CI
#16274
opened Jul 11, 2026 by
trtllm-agent
Collaborator
•
Draft
[None][test] Waive 1 failed cases for main in QA CI
#16273
opened Jul 11, 2026 by
trtllm-agent
Collaborator
•
Draft
[None][test] Waive 9 failed cases for main in QA CI
#16272
opened Jul 11, 2026 by
trtllm-agent
Collaborator
•
Draft
[None][test] Waive 9 failed cases for main in QA CI
#16271
opened Jul 11, 2026 by
trtllm-agent
Collaborator
•
Draft
Cherry pick/pr11143 shared expert fusion v0
#16270
opened Jul 11, 2026 by
leslie-fang25
Collaborator
•
Draft
1 task done
[None][fix] Pass max_num_tokens to MLA KV manager and keep warmup-feasibility floors
#16269
opened Jul 11, 2026 by
qiaoxj07
Collaborator
Loading…
5 tasks done
[TRTLLMINF-191][infra] Preserve pytest progress with S3 capture
#16268
opened Jul 11, 2026 by
niukuo
Collaborator
Loading…
1 task done
[https://nvbugs/6438586][test] verify disagg benchmark fill gate (DO NOT REVIEW / MERGE)
#16267
opened Jul 11, 2026 by
chienchunhung
Collaborator
•
Draft
[https://nvbugs/6435097][fix] Remove the single stale
nvbugs/6427411 waiver line for…
#16266
opened Jul 11, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[https://nvbugs/6434535][fix] Replace boolean-mask indexed writes with a static-shape keep-mask…
#16265
opened Jul 11, 2026 by
trtllm-agent
Collaborator
Loading…
2 tasks done
[None][fix] Align dense Qwen3.5-VL SSM cache dtype test with #16065 semantics
#16264
opened Jul 11, 2026 by
moraxu
Collaborator
Loading…
1 task done
[None][fix] compare library versions with packaging.version, not strings
#16263
opened Jul 10, 2026 by
lonexreb
Loading…
[None][fix] handle empty stream in process_streaming_events
#16262
opened Jul 10, 2026 by
lonexreb
Loading…
[None][fix] avoid UnboundLocalError in CnnDailymail.compute_score
#16261
opened Jul 10, 2026 by
lonexreb
Loading…
[None][fix] validate trtllm-serve --port with ValueError not assert
#16260
opened Jul 10, 2026 by
lonexreb
Loading…
ProTip!
What’s not been updated in a month: updated:<2026-06-12.