Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][test] Remove 60 closed-bug waive entries for main
#15511
opened Jun 21, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 4 failed cases for main in QA CI
#15510
opened Jun 21, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 3 failed cases for main in QA CI
#15509
opened Jun 21, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 7 failed cases for main in QA CI
#15507
opened Jun 20, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 11 failed cases for main in QA CI
#15506
opened Jun 20, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 4 failed cases for main in QA CI
#15505
opened Jun 20, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][test] Waive 9 failed cases for main in QA CI
#15504
opened Jun 20, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][bugfix] Fix executor test response timeout
#15502
opened Jun 19, 2026 by
fallintoplace
Loading…
[None][bugfix] Fix Mamba preloaded HF model loading
#15501
opened Jun 19, 2026 by
fallintoplace
Loading…
[None][fix] Make NIXL port-lock path configurable via TRTLLM_NIXL_PORT_LOCK_PATH
#15500
opened Jun 19, 2026 by
CodersAcademy006
Loading…
4 tasks done
[None][test] Waive 1 failed cases for main in QA CI
#15499
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[https://nvbugs/6329227][fix] Use pkgutil.extend_path to merge the two flash_attn distributions before…
#15498
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6337228][fix] In tests/unittest/tools/test_layer_wise_benchmarks.py, replace check_call with…
#15497
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6316980][fix] Added a runtime guard in FlashInferTrtllmGenAttention.is_supported using the…
#15496
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6341070][fix] Pass kv_cache_free_gpu_memory_fraction=0.5 to TRTLLMWorker.init_with_new_llm…
#15495
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6329165][fix] In TestNemotronNanoV3.test_accuracy, mocker.patch.dict GSM8K.EVALUATE_KWARGS…
#15494
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6341072][fix] Change the model_name fixture to "llama-models-v2/TinyLlama-1.1B-Chat-v1.0"…
#15492
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6337233][fix] In
_build_fake_self, bind PyExecutor._is_stats_dummy_request onto the fake…
#15491
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6337238][fix] Test-only fix — use the existing get_hf_rope_theta helper, adapt the…
#15490
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6337231][fix] Replace all 9
self._is_stats_dummy_request(req) calls with…
#15489
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6335726][fix] In test_qwen_moe_routed_expert_multi_lora_varying_ranks, drop ranks…
#15488
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6337226][fix] Switch
max(positive_hits) → min(positive_hits) in both the range and…
#15487
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6317600][fix] Add an early return at the head of
_run_attention_warmup when…
#15486
opened Jun 19, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] support per-layer mixed-precision MoE serving (GLM, Qwen3-MoE)
#15485
opened Jun 19, 2026 by
joshua-hill
Loading…
ProTip!
What’s not been updated in a month: updated:<2026-05-21.