Skip to content

Actions: EmbeddedLLM/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
513 workflow runs
513 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[PluggableLayer][MM] Add PluggableLayer for CustomQwen2Decoder (#37293) pre-commit #513: Commit 0674d1f pushed by vllmellm
3m 16s main
main
3m 16s
[Feat] Enable CompressedTensorW4A8Int for XPU (#37207) pre-commit #512: Commit 47b7af0 pushed by BadrBasowid
3m 6s main
main
3m 6s
[Perf] Fix slow hasattr in CUDAGraphWrapper.__getattr__ (#37425) pre-commit #511: Commit d3cc379 pushed by tjtanaa
2m 55s main
main
2m 55s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #510: Pull request #78 synchronize by big-yellow-duck
3m 8s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
3m 8s
[ROCm] Enable Aiter ck_gemm_a8w8_blockscale for RDNA4 gpus. Qwen3.5-27B-FP8 tp=2, Qwen3-0.6B-FP8 tp=1 pre-commit #509: Pull request #77 synchronize by big-yellow-duck
3m 6s rdna4-aiter-fp8-blockscale
rdna4-aiter-fp8-blockscale
3m 6s
[Perf] Enable dual stream execution of input projection for Qwen3 (#3… pre-commit #508: Commit f174000 pushed by BadrBasowid
4m 30s main
main
4m 30s
[ROCm] Enable Aiter ck_gemm_a8w8_blockscale for RDNA4 gpus. Qwen3.5-27B-FP8 tp=2, Qwen3-0.6B-FP8 tp=1 pre-commit #507: Pull request #77 synchronize by big-yellow-duck
2m 37s rdna4-aiter-fp8-blockscale
rdna4-aiter-fp8-blockscale
2m 37s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #506: Pull request #78 synchronize by big-yellow-duck
4m 14s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
4m 14s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #505: Pull request #78 synchronize by big-yellow-duck
3m 13s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
3m 13s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #504: Pull request #78 synchronize by big-yellow-duck
2m 59s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
2m 59s
[ROCm] Enable Aiter ck_gemm_a8w8_blockscale for RDNA4 gpus. Qwen3.5-27B-FP8 tp=2, Qwen3-0.6B-FP8 tp=1 pre-commit #503: Pull request #77 synchronize by big-yellow-duck
4m 16s rdna4-aiter-fp8-blockscale
rdna4-aiter-fp8-blockscale
4m 16s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #502: Pull request #78 synchronize by big-yellow-duck
3m 7s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
3m 7s
[ROCm] Enable VLLM triton FP8 moe for gfx1201, tuned for Qwen3-30B-A3B-FP8 tp=2 pre-commit #501: Pull request #79 synchronize by big-yellow-duck
4m 41s rdna4-moe
rdna4-moe
4m 41s
[ROCm] Enable VLLM triton FP8 moe for gfx1201, tuned for Qwen3-30B-A3B-FP8 tp=2 pre-commit #500: Pull request #79 synchronize by big-yellow-duck
3m 4s rdna4-moe
rdna4-moe
3m 4s
[ROCm][P/D][MORI][BugFix] Add transfer_id for moriio_connector so mor… pre-commit #499: Commit 0024f39 pushed by tjtanaa
2m 50s main
main
2m 50s
[responsesAPI][ez] add a unit test for SimpleContext logprobs (#37126) pre-commit #498: Commit e9163b5 pushed by vllmellm
4m 28s main
main
4m 28s
[Hardware] Replace torch.cuda.device_count/current_device/set_device … pre-commit #497: Commit 53ec16a pushed by tanpinsiang
3m 10s main
main
3m 10s
[ROCm] Enable aiter group quant FP8 for RDNA4 gpus pre-commit #496: Pull request #78 opened by big-yellow-duck
3m 5s rdna4-aiter-quantfp8
rdna4-aiter-quantfp8
3m 5s
[ROCm] Enable Aiter ck_gemm_a8w8_blockscale for RDNA4 gpus. Qwen3.5-27B-FP8 tp=2, Qwen3-0.6B-FP8 tp=1 pre-commit #495: Pull request #77 opened by big-yellow-duck
3m 4s rdna4-aiter-fp8-blockscale
rdna4-aiter-fp8-blockscale
3m 4s
[NIXL][1/N] Refactor kernel_block_size detection (#35752) pre-commit #494: Commit 098d844 pushed by tjtanaa
3m 11s main
main
3m 11s
[Bug] Fix TRTLLM Block FP8 MoE Monolithic (#36296) pre-commit #493: Commit 84e436e pushed by vllmellm
4m 23s main
main
4m 23s
[ROCm][CI] Fix logprob divergence for TitanML/tiny-mixtral under AITE… pre-commit #492: Commit 1e0f917 pushed by vllmellm
4m 13s main
main
4m 13s
Reapply [Attention] Refactor check_and_update_config (#35122) pre-commit #491: Commit 77a7345 pushed by vllmellm
5m 17s main
main
5m 17s
Add support for ModelOpt MXFP8 MoE models (#35986) pre-commit #490: Commit 0a6a3a1 pushed by vllmellm
3m 58s main
main
3m 58s
[Bugfix] Fix compressed-tensors quantization failure for DeepSeek-R1 … pre-commit #489: Commit ee8a295 pushed by vllmellm
3m 56s main
main
3m 56s