Skip to content

Activity

Showing most recent first

Update model-feature document (NVIDIA#6243)

QiJunepushed 1 commit to feat/1.0_doc_dev • 6de7985…31d48cd • 
1 hour ago

clean

QiJunepushed 2 commits to model-feature • 068c3f7…2f0f3b8 • 
1 hour ago

update

QiJunepushed 1 commit to model-feature • 43c4c3d…068c3f7 • 
1 hour ago

remove duplicate should_stop_processing check

QiJunecreated clean_loop • 0ff85d0 • 
1 hour ago

feat: Refactor the fetching request logic (NVIDIA#5786)

QiJunepushed 1 commit to main • 7381f1d…ee45e0c • 
2 hours ago

[TRTLLM-5059][feat] Add KV cache reuse support for multimodal models (N…

QiJunepushed 13 commits to main • 88076ee…7381f1d • 
3 hours ago

polish deprecation policy

QiJunepushed 1 commit to deprecation • 41f510b…04258e8 • 
21 hours ago

Merge branch 'main' into deprecation

QiJunepushed 176 commits to deprecation • a044cae…41f510b • 
21 hours ago

[fix] Fix can_use_alltoall in fused_moe_wide_ep.py (NVIDIA#6173)

QiJunepushed 4 commits to main • a433eba…88076ee • 
22 hours ago

add model-feature supported matrix doc (NVIDIA#5914)

QiJunepushed 1 commit to feat/1.0_doc_dev • 8d6ce32…6de7985 • 
22 hours ago

Merge branch 'feat/1.0_doc_dev' into model-feature

QiJunepushed 8 commits to model-feature • 181e2a5…43c4c3d • 
22 hours ago

[TRTLLM-6091][docs] Update docs/trtllm sampler 1.0 (NVIDIA#5833)

QiJunepushed 7 commits to feat/1.0_doc_dev • 447623b…8d6ce32 • 
22 hours ago

enh: Lift expectation of single image per sample in Gemma3 VLM (NVIDI…

QiJunepushed 28 commits to main • c0e4165…a433eba • 
yesterday

polish

QiJunepushed 1 commit to fhma_log • d601f9f…d3cd8df • 
3 days ago

add more log in FmhaDispatcher

QiJunecreated fhma_log • d601f9f • 
3 days ago

fix single_disagg_test (NVIDIA#6166)

QiJunepushed 6 commits to main • ae28b3a…c0e4165 • 
3 days ago

feat: Add support for benchmarking individual gemms in MOE benchmark (N…

QiJunepushed 16 commits to main • e821c68…ae28b3a • 
4 days ago

CI: update multi gpu test trigger file list (NVIDIA#6131)

QiJunepushed 2 commits to main • d4d21a1…e821c68 • 
4 days ago

update

QiJunepushed 1 commit to update_rule_2 • 466cbad…67e5e9f • 
4 days ago

update multi gpu trigger file list

QiJunecreated update_rule_2 • 466cbad • 
4 days ago

[fix] Release slots with spec decode + disagg (NVIDIA#5975) (NVIDIA#6032

QiJunepushed 6 commits to main • 2d2b8ba…d4d21a1 • 
4 days ago

format

QiJunepushed 3 commits to more_log • e5990d6…b551382 • 
5 days ago

implement a safe chunked broadcast

QiJunepushed 1 commit to more_log • 629b844…e5990d6 • 
5 days ago

fix pre commit

QiJunepushed 1 commit to more_log • ed1cd30…629b844 • 
5 days ago

polish

QiJunepushed 1 commit to more_log • 3967b9b…ed1cd30 • 
5 days ago

add more error message for broadcasting new requests

QiJunecreated more_log • 3967b9b • 
5 days ago

feat: TRTLLM-5574 Add phi-4-multimodal pytorch-backend support (NVIDI…

QiJunepushed 83 commits to main • ce39409…2d2b8ba • 
5 days ago

Merge branch 'release/0.21' into release-notes

QiJunepushed 3 commits to release-notes • 7d9f8c9…e32c642 • 
5 days ago

update

QiJunepushed 1 commit to release-notes • 0c5411e…7d9f8c9 • 
5 days ago

update

QiJunepushed 1 commit to release-notes • 52beb0a…0c5411e • 
5 days ago