Workflow runs · NVIDIA/TensorRT-LLM · GitHub

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows

255,687 workflow runs

255,687 workflow runs

L0-Test L0-Test #10501: Manually run by tensorrt-cicd

Queued main

main

Queued

[TRTLLM-8980][test] Clean up spec dec tests in test_llm_api_pytorch Blossom-CI #89797: Issue comment #8889 (comment) created by tensorrt-cicd

1s

1s

[TRTLLM-8980][test] Clean up spec dec tests in test_llm_api_pytorch Bot-Command #85491: Issue comment #8889 (comment) created by tensorrt-cicd

2s

2s

[TRTINFRA-7328][infra] Consume SlurmCluster scratchPath and cleanup mounts Blossom-CI #89796: Issue comment #9600 (comment) created by tensorrt-cicd

1s

1s

[TRTINFRA-7328][infra] Consume SlurmCluster scratchPath and cleanup mounts Bot-Command #85490: Issue comment #9600 (comment) created by tensorrt-cicd

2s

2s

L0-Test L0-Test #10500: Manually run by tensorrt-cicd

35s main

main

35s

[Question] Can I build the tritonserver, tensorrtllm_backend and tensorrtllm and then use these build files across servers? auto-assign #2045: Issue #2423 labeled by karljang

1s

1s

[Question] Can I build the tritonserver, tensorrtllm_backend and tensorrtllm and then use these build files across servers? Blossom-CI #89795: Issue comment #2423 (comment) created by karljang

1s

1s

[Question] Can I build the tritonserver, tensorrtllm_backend and tensorrtllm and then use these build files across servers? Bot-Command #85489: Issue comment #2423 (comment) created by karljang

1s

1s

attempt to run benchmark with batch_size>=512 and input_output_len=1024,128 result in tensor volume exceeds 2147483647 error auto-assign #2044: Issue #2422 labeled by karljang

1s

1s

attempt to run benchmark with batch_size>=512 and input_output_len=1024,128 result in tensor volume exceeds 2147483647 error Blossom-CI #89794: Issue comment #2422 (comment) created by karljang

1s

1s

attempt to run benchmark with batch_size>=512 and input_output_len=1024,128 result in tensor volume exceeds 2147483647 error Bot-Command #85488: Issue comment #2422 (comment) created by karljang

2s

2s

[None][feat] Expost mmKeys for multimodal to integrate with dynamo. Release Checks #30012: Pull request #9604 opened by SimengLiu-nv

In progress SimengLiu-nv:kvcache-mmkeys

SimengLiu-nv:kvcache-mmkeys

In progress

[None][feat] Expost mmKeys for multimodal to integrate with dynamo. PR Checks #22800: Pull request #9604 opened by SimengLiu-nv

13s SimengLiu-nv:kvcache-mmkeys

SimengLiu-nv:kvcache-mmkeys

13s

[Bug]: GPT-OSS-120B One Spec Path - Quality Eval Issue auto-assign #2043: Issue #9603 labeled by harrisonlimh

1s

1s

[Bug]: GPT-OSS-120B One Spec Path - Quality Eval Issue Label New Issues #407: Issue #9603 opened by harrisonlimh

17s

17s

[OMNIML-2932] [feat] nvfp4 awq support Blossom-CI #89793: Issue comment #8698 (comment) created by tensorrt-cicd

3s

3s

[OMNIML-2932] [feat] nvfp4 awq support Bot-Command #85487: Issue comment #8698 (comment) created by tensorrt-cicd

2s

2s

[OMNIML-2932] [feat] nvfp4 awq support Bot-Command #85486: Issue comment #8698 (comment) created by tensorrt-cicd

1s

1s

[OMNIML-2932] [feat] nvfp4 awq support Blossom-CI #89792: Issue comment #8698 (comment) created by tensorrt-cicd

1s

1s

trtllm-bench fail Bot-Command #85485: Issue comment #2476 (comment) created by karljang

3s

3s

trtllm-bench fail Blossom-CI #89791: Issue comment #2476 (comment) created by karljang

4s

4s

[OMNIML-2932] [feat] nvfp4 awq support Blossom-CI #89790: Issue comment #8698 (comment) created by meenchen

4m 57s

4m 57s

[OMNIML-2932] [feat] nvfp4 awq support Bot-Command #85484: Issue comment #8698 (comment) created by meenchen

1s

1s

[OMNIML-2932] [feat] nvfp4 awq support PR Checks #22799: Pull request #8698 synchronize by meenchen

16s meenchen:weimingc/feat/nvfp4_awq

meenchen:weimingc/feat/nvfp4_awq

16s