Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

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
[None][feat] Support skip softmax with KV cache manager V2 Blossom-CI #285188: Issue comment #21553 (comment) created by tensorrt-cicd
1s
1s
[None][feat] Support skip softmax with KV cache manager V2 Bot-Command #280882: Issue comment #21553 (comment) created by tensorrt-cicd
7s
7s
[TRTLLM-16624][fix] Fix Helix MLA decode kernel selection Blossom-CI #285187: Issue comment #21582 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-16624][fix] Fix Helix MLA decode kernel selection Bot-Command #280881: Issue comment #21582 (comment) created by tensorrt-cicd
6s
6s
L0-Test L0-Test #32529: Manually run by tensorrt-cicd
1m 38s main
main
1m 38s
[https://nvbugs/6858496][fix] Fail disagg gen requests whose grammar matcher cannot be created Bot-Command #280880: Issue comment #20903 (comment) created by tensorrt-cicd
8s
8s
[https://nvbugs/6858496][fix] Fail disagg gen requests whose grammar matcher cannot be created Blossom-CI #285186: Issue comment #20903 (comment) created by tensorrt-cicd
8s
8s
L0-Test L0-Test #32528: Manually run by tensorrt-cicd
45s main
main
45s
[None][feat] Support skip softmax with KV cache manager V2 Bot-Command #280879: Issue comment #21553 (comment) created by yizhang-nv
1s
1s
[None][feat] Support skip softmax with KV cache manager V2 Blossom-CI #285185: Issue comment #21553 (comment) created by yizhang-nv
5m 22s
5m 22s
[None][fix] Port native disaggregation KV result report token - #20723 Blossom-CI #285184: Issue comment #21538 (comment) created by tensorrt-cicd
1s
1s
[None][fix] Port native disaggregation KV result report token - #20723 Bot-Command #280878: Issue comment #21538 (comment) created by tensorrt-cicd
1s
1s
L0-Test L0-Test #32527: Manually run by tensorrt-cicd
1m 3s main
main
1m 3s
[TRTLLM-17054][refactor] Reuse sampling synchronization and sequence slots across warmup phases Bot-Command #280877: Issue comment #20813 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-17054][refactor] Reuse sampling synchronization and sequence slots across warmup phases Blossom-CI #285183: Issue comment #20813 (comment) created by tensorrt-cicd
8s
8s
L0-Test L0-Test #32526: Manually run by tensorrt-cicd
40s main
main
40s
[None][test] Add GB200 Qwen3-235B FP4 and GLM-5 FP4 perf-sanity cases to the QA multi-node perf list Sync LFS Objects After Merge #6886: Pull request #21620 closed by chenfeiz0326
2s
2s
[TRTLLM-17123][feat] Gather cached MLA KV for Helix prefill Bot-Command #280876: Issue comment #21527 (comment) created by tensorrt-cicd
1s
1s
[TRTLLM-17123][feat] Gather cached MLA KV for Helix prefill Blossom-CI #285182: Issue comment #21527 (comment) created by tensorrt-cicd
1s
1s
[TRTLLMINF-439][infra] Add rubin SBSA single gpu tests in post-merge Bot-Command #280875: Issue comment #19195 (comment) created by tensorrt-cicd
11s
11s
[TRTLLMINF-439][infra] Add rubin SBSA single gpu tests in post-merge Blossom-CI #285181: Issue comment #19195 (comment) created by tensorrt-cicd
7s
7s
[TRTLLM-14978][perf] Kimi-K3 decode attention-residual kernel: CuTe DSL PDL mix with the MoE residual folded in, MXFP8 hand-off to KDA, gated/sigmoid low-M GEMM variants Blossom-CI #285180: Issue comment #21399 (comment) created by longlee0622
5m 40s
5m 40s
[TRTLLM-14978][perf] Kimi-K3 decode attention-residual kernel: CuTe DSL PDL mix with the MoE residual folded in, MXFP8 hand-off to KDA, gated/sigmoid low-M GEMM variants Bot-Command #280874: Issue comment #21399 (comment) created by longlee0622
1s
1s
L0-Test L0-Test #32525: Manually run by tensorrt-cicd
1m 44s main
main
1m 44s
[None][feat] Responses: name the engine request behind each reply Bot-Command #280873: Issue comment #21602 (comment) created by tensorrt-cicd
1s
1s