Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][fix] configure DeepGEMM PDL during engine init
#15004
opened Jun 5, 2026 by
liji-nv
Collaborator
Loading…
1 task done
[None][fix] tunable_fp4_quantize: rename misnamed kwarg + add real SF-swizzle control
#15002
opened Jun 5, 2026 by
luyiyun1021
Collaborator
Loading…
1 task done
[None][fix] Uncomment Qwen3.5 and DSR1 from model registry so that they can run f…
#15001
opened Jun 5, 2026 by
taylor-yb-lee
Collaborator
Loading…
1 task done
[https://nvbugs/6215793][fix] Thread ctx_total_kv_len through getWorkspaceSize→getWorkspaceSizeForContext…
#15000
opened Jun 5, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] Weight trtllm-bench AR/AL averages by output length
#14998
opened Jun 5, 2026 by
zhaoyangwang-nvidia
Collaborator
Loading…
1 task done
[None][test] Add K25 EPLB
#14996
opened Jun 5, 2026 by
chenfeiz0326
Collaborator
Loading…
1 task done
[None][perf] kv_cache_manager_v2: batch block-key SHA-256 hashing
#14994
opened Jun 5, 2026 by
lancelly
Collaborator
Loading…
[https://nvbugs/6224637][test] unwaive associated tests
#14993
opened Jun 5, 2026 by
yuxianq
Collaborator
Loading…
feat(visual_gen): add HunyuanDiT text-to-image pipeline with Ulysses parallelism
#14991
opened Jun 5, 2026 by
pkisfaludi-nv
Loading…
4 tasks
[None][test] Add gpt-oss-120b eagle3 accuracy test
#14990
opened Jun 5, 2026 by
JennyLiu-nv
Collaborator
Loading…
1 task done
[None][feat] Support post-norm and per-aux fc_norm for Eagle3 draft models
#14988
opened Jun 5, 2026 by
Dogacel
Loading…
1 task done
[None][feat] add FLUX visual generation examples
#14987
opened Jun 5, 2026 by
karljang
Collaborator
Loading…
1 task done
[None][fix] guard CUDA graph capture against ADP asymmetric batch-None deadlock
#14986
opened Jun 5, 2026 by
longcheng-nv
Collaborator
Loading…
2 tasks done
[TRTLLM-12838][infra] enhance code coverage for catching subprocess data
#14985
opened Jun 5, 2026 by
crazydemo
Collaborator
Loading…
1 task done
[None][feat] Cache LTX2 merged LoRA weight
#14984
opened Jun 5, 2026 by
yibinl-nvidia
Collaborator
•
Draft
1 task
[None][feat] add Wan I2V generation example
#14981
opened Jun 5, 2026 by
o-stoner
Collaborator
Loading…
1 task done
[None][feat] Add mxfp8 output dtype to Fmha
#14980
opened Jun 4, 2026 by
IwakuraRein
Contributor
•
Draft
1 task done
[https://nvbugs/6104831][fix] Port dataTransceiver shared_ptr<LlmRequest> lifetime fix
#14979
opened Jun 4, 2026 by
chienchunhung
Collaborator
Loading…
[None][test] Update DGX spark CI/QA tests
#14978
opened Jun 4, 2026 by
pamelap-nvidia
Collaborator
Loading…
1 task done
[https://nvbugs/6250866][fix] Fix deep ep partial warp sync for gptoss shapes
#14977
opened Jun 4, 2026 by
dongfengy
Collaborator
Loading…
1 task done
[None][feat] Add LTX-2 visual generation example
#14976
opened Jun 4, 2026 by
yibinl-nvidia
Collaborator
Loading…
1 task done
[None][perf] Remove redundant allreduce
deepseek-v4
#14974
opened Jun 4, 2026 by
mikeiovine
Collaborator
Loading…
1 task done
[https://nvbugs/6266705][fix] Gate the FlashInfer import-time selection on
get_sm_version() == 90 (in…
#14973
opened Jun 4, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][infra] Reduce Docker image layer count in release stage
#14972
opened Jun 4, 2026 by
tburt-nv
Collaborator
Loading…
1 task done
ProTip!
Filter pull requests by the default branch with base:main.