Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

Bot-Command

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
bot-command.yml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[TRTLLM-15757][refactor] Land the ModelRunner contract with the no-KVCache families Bot-Command #241739: Issue comment #18784 (comment) created by tensorrt-cicd
9s
9s
[None][infra] Skip pre-merge perf gating when main has already regressed and refactor the pre-merge perf-sanity list Bot-Command #241738: Issue comment #18766 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-16012][feat] Restrict torch.compile to piecewise graph capture only Bot-Command #241737: Issue comment #18366 (comment) created by AlessioNetti
Skipped
Skipped
[None][fix] Raise SetupError instead of NameError when the precompiled wheel is missing Bot-Command #241736: Issue comment #18703 (comment) created by tensorrt-cicd
9s
9s
[TRTLLM-16212][feat] Unified caching via TRTLLM_CACHE_DIR environment variable Bot-Command #241735: Issue comment #18897 (comment) created by AlessioNetti
1s
1s
[None][feat] Derive per-layer KV cache windows from layer_types Bot-Command #241734: Issue comment #18767 (comment) created by tensorrt-cicd
1s
1s
[None][infra] Skip pre-merge perf gating when main has already regressed and refactor the pre-merge perf-sanity list Bot-Command #241733: Issue comment #18766 (comment) created by chenfeiz0326
9s
9s
[None][feat] Develop agent flow orchestration and support parallel execution of perf agent and modeling agent based on it Bot-Command #241732: Issue comment #18876 (comment) created by tensorrt-cicd
1s
1s
[None][fix] Raise SetupError instead of NameError when the precompiled wheel is missing Bot-Command #241731: Issue comment #18703 (comment) created by tburt-nv
2s
2s
[None][feat] Develop agent flow orchestration and support parallel execution of perf agent and modeling agent based on it Bot-Command #241730: Issue comment #18876 (comment) created by WeiHaocheng
1s
1s
[None][perf] Apply NUMA-aware CPU affinity beyond the main thread Bot-Command #241729: Issue comment #18701 (comment) created by tensorrt-cicd
1s
1s
[https://nvbugs/6707519][fix] Re-land attempt 1 verbatim on the current tip — add… Bot-Command #241728: Issue comment #18629 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-15757][refactor] Land the ModelRunner contract with the no-KVCache families Bot-Command #241727: Issue comment #18784 (comment) created by tensorrt-cicd
1s
1s
[None][feat] Develop agent flow orchestration and support parallel execution of perf agent and modeling agent based on it Bot-Command #241726: Issue comment #18876 (comment) created by coderabbitai Bot
1s
1s
[https://nvbugs/6676312][fix] Restore DSA CUDA TopK workspace lifecycle Bot-Command #241725: Issue comment #18624 (comment) created by tensorrt-cicd
2s
2s
[None][feat] Add a link mode to the precompiled editable-install path Bot-Command #241724: Issue comment #18752 (comment) created by tensorrt-cicd
1s
1s
[None][feat] support disaggregated serving for Qwen3.8-Flash-Next Bot-Command #241723: Issue comment #18921 (comment) created by tensorrt-cicd
7s
7s
[TRTLLM-16186][fix] Correct the disagg handoff: planning, alignment, gates Bot-Command #241722: Issue comment #18819 (comment) created by tensorrt-cicd
2s
2s
[None][perf] fuse decode kernel seams for Qwen3.8-Flash-Next and de-vendor the low-M GEMMs Bot-Command #241721: Issue comment #18883 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-15757][refactor] Land the ModelRunner contract with the no-KVCache families Bot-Command #241720: Issue comment #18784 (comment) created by lori-ren
1s
1s
[None][feat] Add a link mode to the precompiled editable-install path Bot-Command #241719: Issue comment #18752 (comment) created by tensorrt-cicd
1s
1s
[None][feat] Derive per-layer KV cache windows from layer_types Bot-Command #241718: Issue comment #18767 (comment) created by tensorrt-cicd
2s
2s
[None][perf] Apply NUMA-aware CPU affinity beyond the main thread Bot-Command #241717: Issue comment #18701 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-12499][perf] Bounded block-ID retrieval for pipelined KV transfer chunks Bot-Command #241716: Issue comment #17526 (comment) created by mikeiovine
8s
8s
[https://nvbugs/6676312][fix] Restore DSA CUDA TopK workspace lifecycle Bot-Command #241715: Issue comment #18624 (comment) created by tensorrt-cicd
1s
1s