Skip to content

Actions: ROCm/vllm

Cleanup PR Body

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
96 workflow runs
96 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[CI]Enable branch llama_fp8_12062024 for github actions for PR checks
Cleanup PR Body #96: Pull request #355 edited by hongxiayang
January 10, 2025 20:32 14s
January 10, 2025 20:32 14s
[CI]Enable branch llama_fp8_12062024 for github actions for PR checks
Cleanup PR Body #95: Pull request #355 opened by hongxiayang
January 10, 2025 20:21 23s
January 10, 2025 20:21 23s
[Cleanup] Remove obsolete patches and references and test CI
Cleanup PR Body #94: Pull request #354 opened by hongxiayang
January 9, 2025 23:55 19s
January 9, 2025 23:55 19s
change the queue for the jobs
Cleanup PR Body #93: Pull request #353 opened by hongxiayang
January 9, 2025 23:18 22s
January 9, 2025 23:18 22s
Deepseek V2 FP8 support
Cleanup PR Body #92: Pull request #352 reopened by Concurrensee
January 9, 2025 18:43 15s
January 9, 2025 18:43 15s
Deepseek V2 FP8 support
Cleanup PR Body #91: Pull request #352 opened by Concurrensee
January 9, 2025 18:37 15s
January 9, 2025 18:37 15s
Revert nccl changes
Cleanup PR Body #90: Pull request #351 opened by gshtras
January 8, 2025 21:23 19s
January 8, 2025 21:23 19s
Upstream merge 25 1 6
Cleanup PR Body #89: Pull request #350 opened by gshtras
January 6, 2025 23:22 23s
January 6, 2025 23:22 23s
deepseek overflow fix
Cleanup PR Body #88: Pull request #349 opened by Concurrensee
January 6, 2025 22:10 17s
January 6, 2025 22:10 17s
add video group for test user
Cleanup PR Body #87: Pull request #348 opened by dhonnappa-amd
January 6, 2025 20:12 24s
January 6, 2025 20:12 24s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v2)
Cleanup PR Body #86: Pull request #347 edited by tjtanaa
December 27, 2024 16:33 19s
December 27, 2024 16:33 19s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
Cleanup PR Body #85: Pull request #346 edited by tjtanaa
December 27, 2024 16:33 15s
December 27, 2024 16:33 15s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
Cleanup PR Body #84: Pull request #346 edited by tjtanaa
December 27, 2024 16:33 21s
December 27, 2024 16:33 21s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v2)
Cleanup PR Body #83: Pull request #347 opened by tjtanaa
December 27, 2024 16:32 19s
December 27, 2024 16:32 19s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
Cleanup PR Body #82: Pull request #346 edited by tjtanaa
December 24, 2024 05:41 23s
December 24, 2024 05:41 23s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
Cleanup PR Body #81: Pull request #346 edited by tjtanaa
December 24, 2024 05:41 22s
December 24, 2024 05:41 22s
[FEAT] Improved PagedAttention FP8 (faster kvcache dequant v1)
Cleanup PR Body #80: Pull request #346 opened by tjtanaa
December 24, 2024 05:33 20s
December 24, 2024 05:33 20s
Updated fused_moe configs for MI325X with Triton 3.2
Cleanup PR Body #79: Pull request #345 opened by JArnoldAMD
December 21, 2024 02:21 24s
December 21, 2024 02:21 24s
Update MI300X fused_moe configs for Triton 3.2
Cleanup PR Body #78: Pull request #344 opened by JArnoldAMD
December 20, 2024 20:59 23s
December 20, 2024 20:59 23s
Library versions bump
Cleanup PR Body #77: Pull request #343 opened by gshtras
December 20, 2024 16:00 26s
December 20, 2024 16:00 26s
[Fix] fix_vllm_moe_quant
Cleanup PR Body #76: Pull request #342 opened by lihaoyang-amd
December 20, 2024 10:24 24s
December 20, 2024 10:24 24s
[Fix] fix_vllm_moe_quant
Cleanup PR Body #75: Pull request #341 edited by lihaoyang-amd
December 20, 2024 04:08 22s
December 20, 2024 04:08 22s
[Fix] fix_vllm_moe_quant
Cleanup PR Body #74: Pull request #341 opened by lihaoyang-amd
December 20, 2024 04:05 15s
December 20, 2024 04:05 15s
Ingest FP8 attn scales and use them in ROCm FlashAttention
Cleanup PR Body #73: Pull request #338 edited by mawong-amd
December 19, 2024 23:23 23s
December 19, 2024 23:23 23s
Ingest FP8 attn scales and use them in ROCm FlashAttention
Cleanup PR Body #72: Pull request #338 edited by mawong-amd
December 19, 2024 23:22 20s
December 19, 2024 23:22 20s