Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][chore] Make submit.py can run single GPU test and accept customized config file
#14630
opened May 27, 2026 by
HuiGao-NV
Collaborator
Loading…
1 task done
[None][fix] unwaive TestNemotronNanoV3 tests
#14628
opened May 27, 2026 by
tcherckez-nvidia
Collaborator
Loading…
1 task done
[TRTLLM-13017][fix] disagg gen init: use prompt_len for SWA history_length
#14627
opened May 27, 2026 by
Shixiaowei02
Collaborator
Loading…
1 task done
[https://nvbugs/6094100][fix] add ucx tls env in disagg related tests
#14626
opened May 27, 2026 by
chuangz0
Collaborator
Loading…
1 task done
[None][infra] Fix hang when generating report
#14625
opened May 27, 2026 by
EmmaQiaoCh
Collaborator
Loading…
1 task done
[https://nvbugs/6221841][fix] Detect via the raw config_dict whether the user actually set a top-level rope_th
#14624
opened May 27, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] add DSV4 KV cache pool ratio config
#14623
opened May 27, 2026 by
jiaganc
Collaborator
Loading…
1 task done
[None][doc] Add CUTLASS DSL uninstall step to installation guide
#14621
opened May 27, 2026 by
yihwang-nv
Collaborator
Loading…
2 tasks
[None][feat] Default on FlashInferTrtllmGenAttention
#14618
opened May 27, 2026 by
yihwang-nv
Collaborator
Loading…
[None][fix] fix Qwen-VL processor _defaults mutation at the source
#14617
opened May 27, 2026 by
longlee0622
Collaborator
•
Draft
1 task
[TRTLLM-8236][infra] fix platform tag for public wheel
#14616
opened May 27, 2026 by
niukuo
Collaborator
Loading…
1 task done
[https://nvbugs/6193836][test] Use EP=8 + attention DP for minimax_m2.5 8-GPU perf
#14613
opened May 27, 2026 by
ruodil
Collaborator
Loading…
1 task done
[None][feat] Support tool-calling in KvCacheAwareRouter for disagg serving (feat/deepseek_v4)
#14611
opened May 27, 2026 by
lishicheng1996-nv
Collaborator
Loading…
1 task done
[None][infra] Switch platform to aws-dfw for GB200 to test
#14610
opened May 27, 2026 by
yuanjingx87
Collaborator
•
Draft
1 task
[None][feat] Add TRTLLM_SKIP_MAX_SHAPE_WARMUP env var for disaggregated case
#14609
opened May 27, 2026 by
dominicshanshan
Collaborator
•
Draft
1 task done
[Draft][TRTLLM-12950][feat] Add MegaMoECuteDsl NVFP4 MoE backend
#14608
opened May 27, 2026 by
xxi-nv
Collaborator
Loading…
[None][chore] Update flashinfer-python from 0.6.12rc1 to 0.6.12rc2
#14607
opened May 27, 2026 by
yihwang-nv
Collaborator
Loading…
4 tasks
[https://nvbugs/6226287][fix] Made GeneralExecSettings.eos_id Optional[int]=None and resolved it after Runtime
#14606
opened May 27, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][fix] MegaMoEDeepGemm: use engine max_num_tokens directly
#14605
opened May 27, 2026 by
mingyangHao
Collaborator
Loading…
1 task done
[None][fix] make bypass_processor_output_validation thread-safe
#14604
opened May 27, 2026 by
longlee0622
Collaborator
•
Draft
1 of 3 tasks
ProTip!
no:milestone will show everything without a milestone.