Skip to content

Actions: NVIDIA/TensorRT-LLM

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
95,336 workflow runs
95,336 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Blossom-CI #37345: Issue comment #5817 (comment) created by tensorrt-cicd
July 8, 2025 22:54 1s
July 8, 2025 22:54 1s
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Bot-Command #33041: Issue comment #5817 (comment) created by tensorrt-cicd
July 8, 2025 22:54 Skipped
July 8, 2025 22:54 Skipped
feat: Custom masking utils for Gemma3 VLM Blossom-CI #37344: Issue comment #5853 (comment) created by brb-nv
July 8, 2025 22:49 1s
July 8, 2025 22:49 1s
feat: Custom masking utils for Gemma3 VLM Bot-Command #33040: Issue comment #5853 (comment) created by brb-nv
July 8, 2025 22:49 1s
July 8, 2025 22:49 1s
feat: Custom masking utils for Gemma3 VLM Blossom-CI #37343: Issue comment #5853 (comment) created by chang-l
July 8, 2025 22:44 1s
July 8, 2025 22:44 1s
feat: Custom masking utils for Gemma3 VLM Bot-Command #33039: Issue comment #5853 (comment) created by chang-l
July 8, 2025 22:44 1s
July 8, 2025 22:44 1s
Guided decoding is not supported with overlap scheduler Blossom-CI #37342: Issue comment #5858 (comment) created by laikhtewari
July 8, 2025 22:40 1s
July 8, 2025 22:40 1s
Guided decoding is not supported with overlap scheduler Bot-Command #33038: Issue comment #5858 (comment) created by laikhtewari
July 8, 2025 22:40 1s
July 8, 2025 22:40 1s
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Bot-Command #33037: Issue comment #5817 (comment) created by tensorrt-cicd
July 8, 2025 22:39 1s
July 8, 2025 22:39 1s
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Blossom-CI #37341: Issue comment #5817 (comment) created by tensorrt-cicd
July 8, 2025 22:39 1s
July 8, 2025 22:39 1s
support TRTLLM_DEEP_EP_TOKEN_LIMIT to allow run deep-ep on memory-con… Bot-Command #33036: Issue comment #5684 (comment) created by tensorrt-cicd
July 8, 2025 22:39 1s
July 8, 2025 22:39 1s
support TRTLLM_DEEP_EP_TOKEN_LIMIT to allow run deep-ep on memory-con… Blossom-CI #37340: Issue comment #5684 (comment) created by tensorrt-cicd
July 8, 2025 22:39 1s
July 8, 2025 22:39 1s
Running DeepSeek R1 on 8x RTX 6000 PRO Bot-Command #33035: Issue comment #5581 (comment) created by SimengLiu-nv
July 8, 2025 22:38 Skipped
July 8, 2025 22:38 Skipped
Running DeepSeek R1 on 8x RTX 6000 PRO Blossom-CI #37339: Issue comment #5581 (comment) created by SimengLiu-nv
July 8, 2025 22:38 2s
July 8, 2025 22:38 2s
chore: remove support for llmapi + TRT backend in Triton Bot-Command #33034: Issue comment #5856 (comment) created by tensorrt-cicd
July 8, 2025 22:37 6s
July 8, 2025 22:37 6s
chore: remove support for llmapi + TRT backend in Triton Blossom-CI #37338: Issue comment #5856 (comment) created by tensorrt-cicd
July 8, 2025 22:37 1s
July 8, 2025 22:37 1s
chore: remove support for llmapi + TRT backend in Triton Blossom-CI #37337: Issue comment #5856 (comment) created by tensorrt-cicd
July 8, 2025 22:37 1s
July 8, 2025 22:37 1s
chore: remove support for llmapi + TRT backend in Triton Bot-Command #33033: Issue comment #5856 (comment) created by tensorrt-cicd
July 8, 2025 22:37 Skipped
July 8, 2025 22:37 Skipped
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Bot-Command #33032: Issue comment #5817 (comment) created by moraxu
July 8, 2025 22:34 1s
July 8, 2025 22:34 1s
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Blossom-CI #37336: Issue comment #5817 (comment) created by moraxu
July 8, 2025 22:34 4m 39s
July 8, 2025 22:34 4m 39s
[Feature] Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache Release Checks #12400: Pull request #5817 synchronize by moraxu
July 8, 2025 22:33 3m 43s moraxu:dev-mguzek-enable-fail-fast-when-attention-window-too-large
moraxu:dev-mguzek-enable-fail-fast-when-attention-window-too-large
July 8, 2025 22:33 3m 43s
Running DeepSeek R1 on 8x RTX 6000 PRO Bot-Command #33031: Issue comment #5581 (comment) created by grimulkan
July 8, 2025 22:32 1s
July 8, 2025 22:32 1s
Running DeepSeek R1 on 8x RTX 6000 PRO Blossom-CI #37335: Issue comment #5581 (comment) created by grimulkan
July 8, 2025 22:32 1s
July 8, 2025 22:32 1s
chore: remove support for llmapi + TRT backend in Triton Blossom-CI #37334: Issue comment #5856 (comment) created by achartier
July 8, 2025 22:31 4m 32s
July 8, 2025 22:31 4m 32s
chore: remove support for llmapi + TRT backend in Triton Bot-Command #33030: Issue comment #5856 (comment) created by achartier
July 8, 2025 22:31 1s
July 8, 2025 22:31 1s