Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[TRTLLM-13248][feat] Wave 3: migrate MoE staged hooks
#15386
opened Jun 15, 2026 by
chienchunhung
Collaborator
•
Draft
[None][feat] DSv4 prep: attention op plumbing
#15384
opened Jun 15, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[None][feat] Add Gemma-4 NVFP4 quantized models to AutoDeploy registry
#15382
opened Jun 15, 2026 by
marinayanov
Collaborator
Loading…
[None][feat] DSv4 prep: IndexerTopK and TopK primitives
#15381
opened Jun 15, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[https://nvbugs/6278377][fix] Prepend a no-quant baseline entry (
- accuracy: 88) under…
#15380
opened Jun 15, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] DSv4 prep: compressor and mHC primitives
#15379
opened Jun 15, 2026 by
lfr-0531
Collaborator
Loading…
[None][feat] DSv4 prep: runtime cache foundations
#15378
opened Jun 15, 2026 by
lfr-0531
Collaborator
Loading…
[None][test] Waive 1 failed cases for main in QA CI
#15377
opened Jun 15, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][refactor] Enhance pytest integration by updating test node generation to support fixture inheritance and dynamic collection
#15374
opened Jun 15, 2026 by
yufeiwu-nv
Collaborator
Loading…
1 task done
[None][infra] Waive 21 failed cases for main in post-merge 2780
#15373
opened Jun 15, 2026 by
ZhanruiSunCh
Collaborator
Loading…
[None][perf] LTX-2: pad short audio seqlen >128 to keep audio cross-attn on cuDNN SM100
#15371
opened Jun 15, 2026 by
luyiyun1021
Collaborator
Loading…
1 task done
[None][feat] fuse NVFP4 input-quant into v_b_proj BMM epilogue
#15370
opened Jun 15, 2026 by
JunyiXu-nv
Collaborator
•
Draft
1 task
[https://nvbugs/312578][fix] split test_cache_transceiver_single_process
#15369
opened Jun 15, 2026 by
chuangz0
Collaborator
Loading…
1 task done
[None][infra] Improve unit test CI coverage
#15368
opened Jun 15, 2026 by
yuxianq
Collaborator
Loading…
1 task done
[https://nvbugs/6312578][fix] Replace the single file-level entry in
l0_h100.yml with three function-level…
#15365
opened Jun 15, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][infra] Update the new duration base on opensearch result
#15364
opened Jun 15, 2026 by
EmmaQiaoCh
Collaborator
Loading…
1 task done
[https://nvbugs/6179661][fix] Fix disagg generation-side KV transfer timeout deadlocks and teardown crashes
#15363
opened Jun 15, 2026 by
nv-xtf
Collaborator
Loading…
1 task done
[None][perf] avoid full input_token_ids copy in ADP router token count
#15362
opened Jun 15, 2026 by
lancelly
Collaborator
Loading…
[TRTLLM-12762][test] Add multi-node TP coverage for MiniMax-M2
#15361
opened Jun 15, 2026 by
jieli-matrix
Collaborator
Loading…
1 task done
ProTip!
Mix and match filters to narrow down what you’re looking for.