Skip to content

Actions: vllm-project/vllm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
170,807 workflow runs
170,807 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. pre-commit #10981: Pull request #13932 synchronize by bnellnm
March 31, 2025 22:06 In progress neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 22:06 In progress
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. Lint and Deploy Charts #13263: Pull request #13932 synchronize by bnellnm
March 31, 2025 22:06 In progress neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 22:06 In progress
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. Lint and Deploy Charts #13262: Pull request #13932 synchronize by bnellnm
March 31, 2025 21:27 5m 59s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 21:27 5m 59s
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. pre-commit #10980: Pull request #13932 synchronize by bnellnm
March 31, 2025 21:27 5m 4s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 21:27 5m 4s
[torch.compile][TPU] Make @support_torch_compile work for XLA backend Cleanup PR Body #7295: Pull request #15782 edited by lsy323
March 31, 2025 21:26 10s
March 31, 2025 21:26 10s
[Performance][ROCm] Add skinny gemms for unquantized linear on ROCm Lint and Deploy Charts #13261: Pull request #15830 synchronize by charlifu
March 31, 2025 21:26 6m 23s ROCm:charlifu/amd_skinny_gemm
ROCm:charlifu/amd_skinny_gemm
March 31, 2025 21:26 6m 23s
[Performance][ROCm] Add skinny gemms for unquantized linear on ROCm pre-commit #10979: Pull request #15830 synchronize by charlifu
March 31, 2025 21:26 5m 20s ROCm:charlifu/amd_skinny_gemm
ROCm:charlifu/amd_skinny_gemm
March 31, 2025 21:26 5m 20s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7294: Pull request #15720 edited by maleksan85
March 31, 2025 21:25 11s
March 31, 2025 21:25 11s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7293: Pull request #15720 edited by maleksan85
March 31, 2025 21:25 12s
March 31, 2025 21:25 12s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7292: Pull request #15720 edited by maleksan85
March 31, 2025 21:24 11s
March 31, 2025 21:24 11s
[ROCm][Bugfix] Bring back fallback to eager mode removed in #14917, but for ROCm only Lint and Deploy Charts #13260: Pull request #15413 synchronize by gshtras
March 31, 2025 21:23 5m 59s ROCm:mllama_rocm_eager
ROCm:mllama_rocm_eager
March 31, 2025 21:23 5m 59s
[ROCm][Bugfix] Bring back fallback to eager mode removed in #14917, but for ROCm only pre-commit #10978: Pull request #15413 synchronize by gshtras
March 31, 2025 21:23 5m 4s ROCm:mllama_rocm_eager
ROCm:mllama_rocm_eager
March 31, 2025 21:23 5m 4s
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. Lint and Deploy Charts #13259: Pull request #13932 synchronize by bnellnm
March 31, 2025 21:16 6m 8s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 21:16 6m 8s
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. pre-commit #10977: Pull request #13932 synchronize by bnellnm
March 31, 2025 21:16 4m 43s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 21:16 4m 43s
[ROCM][KERNEL] Paged attention for V1 pre-commit #10976: Pull request #15720 synchronize by maleksan85
March 31, 2025 21:08 5m 8s ROCm:v1_rocm_paged_attention_integration
ROCm:v1_rocm_paged_attention_integration
March 31, 2025 21:08 5m 8s
[ROCM][KERNEL] Paged attention for V1 Lint and Deploy Charts #13258: Pull request #15720 synchronize by maleksan85
March 31, 2025 21:08 6m 4s ROCm:v1_rocm_paged_attention_integration
ROCm:v1_rocm_paged_attention_integration
March 31, 2025 21:08 6m 4s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7291: Pull request #15720 edited by maleksan85
March 31, 2025 21:03 13s
March 31, 2025 21:03 13s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7290: Pull request #15720 edited by maleksan85
March 31, 2025 20:55 15s
March 31, 2025 20:55 15s
[ROCM][KERNEL] Paged attention for V1 Cleanup PR Body #7289: Pull request #15720 edited by maleksan85
March 31, 2025 20:53 11s
March 31, 2025 20:53 11s
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. pre-commit #10975: Pull request #13932 synchronize by bnellnm
March 31, 2025 20:48 5m 9s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 20:48 5m 9s
Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. Lint and Deploy Charts #13257: Pull request #13932 synchronize by bnellnm
March 31, 2025 20:48 6m 20s neuralmagic:deep-gemm
neuralmagic:deep-gemm
March 31, 2025 20:48 6m 20s
Move dockerfiles into their own directory (#14549) pre-commit #10974: Commit e6e3c55 pushed by simon-mo
March 31, 2025 20:47 5m 5s main
main
March 31, 2025 20:47 5m 5s
Push on main CodeQL #3207: by simon-mo
March 31, 2025 20:47 2m 57s main
main
March 31, 2025 20:47 2m 57s
Added the option of returning hidden states pre-commit #10973: Pull request #15434 synchronize by Settheworldonfireiii
March 31, 2025 20:37 5m 4s Settheworldonfireiii:main
Settheworldonfireiii:main
March 31, 2025 20:37 5m 4s
Added the option of returning hidden states Lint and Deploy Charts #13256: Pull request #15434 synchronize by Settheworldonfireiii
March 31, 2025 20:37 6m 24s Settheworldonfireiii:main
Settheworldonfireiii:main
March 31, 2025 20:37 6m 24s