Skip to content

Actions: vllm-project/vllm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
290,612 workflow runs
290,612 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Performance]: Custom Helion Kernels Label issues based on keywords #6899: Issue #32962 edited by xiaohongchen1991
Queued
Queued
[WIP][Kernel] Add Helion kernel for rms_norm_dynamic_per_token_quant BC Lint #58043: Pull request #34432 opened by xiaohongchen1991
Queued xiaohongchen1991:rms_norm_dynamic_per_token_quant
xiaohongchen1991:rms_norm_dynamic_per_token_quant
Queued
[WIP][Kernel] Add Helion kernel for rms_norm_dynamic_per_token_quant pre-commit #90939: Pull request #34432 opened by xiaohongchen1991
In progress xiaohongchen1991:rms_norm_dynamic_per_token_quant
xiaohongchen1991:rms_norm_dynamic_per_token_quant
In progress
[WIP][Kernel] Add Helion kernel for rms_norm_dynamic_per_token_quant PR Reminder Comment Bot #17689: Pull request #34432 opened by xiaohongchen1991
1m 55s
1m 55s
[WIP][Kernel] Add Helion kernel for rms_norm_dynamic_per_token_quant Cleanup PR Body #43481: Pull request #34432 opened by xiaohongchen1991
1m 32s
1m 32s
[WIP][Kernel] Add Helion kernel for dynamic_per_tensor_scaled_fp8_quant Cleanup PR Body #43480: Pull request #33867 edited by xiaohongchen1991
20s
20s
[Perf] fused_moe: add int4_w4a16 benchmark support and tuning config pre-commit #90938: Pull request #34130 synchronize by mgehre-amd
4m 2s mgehre-amd:matthias.moe_int4_benchmark
mgehre-amd:matthias.moe_int4_benchmark
4m 2s
[Perf] fused_moe: add int4_w4a16 benchmark support and tuning config BC Lint #58042: Pull request #34130 synchronize by mgehre-amd
23s mgehre-amd:matthias.moe_int4_benchmark
mgehre-amd:matthias.moe_int4_benchmark
23s
[KVConnector] Auto-downgrade to PIECEWISE cudagraph mode for layerwise async ops pre-commit #90937: Pull request #31057 synchronize by ProExpertProg
3m 56s yashwantbezawada:fix/kv-connector-piecewise-cudagraph
yashwantbezawada:fix/kv-connector-piecewise-cudagraph
3m 56s
[KVConnector] Auto-downgrade to PIECEWISE cudagraph mode for layerwise async ops BC Lint #58041: Pull request #31057 synchronize by ProExpertProg
22s yashwantbezawada:fix/kv-connector-piecewise-cudagraph
yashwantbezawada:fix/kv-connector-piecewise-cudagraph
22s
[KVConnector] Auto-downgrade to PIECEWISE cudagraph mode for layerwise async ops BC Lint #58040: Pull request #31057 labeled by ProExpertProg
15s yashwantbezawada:fix/kv-connector-piecewise-cudagraph
yashwantbezawada:fix/kv-connector-piecewise-cudagraph
15s
[ROCm][quantization] improve OCP weight quant parser robust Cleanup PR Body #43479: Pull request #34431 edited by xuebwang-amd
22s
22s
[ROCm][quantization] improve OCP weight quant parser robust BC Lint #58039: Pull request #34431 labeled by mergify bot
22s xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
22s
[Bugfix] FIx torchao-config BC Lint #58038: Pull request #34430 unlabeled by mergify bot
23s jwpark33:hf-overrides-file
jwpark33:hf-overrides-file
23s
[ROCm][quantization] improve OCP weight quant parser robust BC Lint #58037: Pull request #34431 opened by xuebwang-amd
25s xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
25s
[ROCm][quantization] improve OCP weight quant parser robust pre-commit #90936: Pull request #34431 opened by xuebwang-amd
3m 55s xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
xuebwang-amd:xuebin_fix_quark_ocp_weight_parser
3m 55s
[ROCm][quantization] improve OCP weight quant parser robust PR Reminder Comment Bot #17688: Pull request #34431 opened by xuebwang-amd
9s
9s
[ROCm][quantization] improve OCP weight quant parser robust Cleanup PR Body #43478: Pull request #34431 opened by xuebwang-amd
20s
20s
[Bugfix] FIx torchao-config BC Lint #58036: Pull request #34430 synchronize by jwpark33
22s jwpark33:hf-overrides-file
jwpark33:hf-overrides-file
22s
[Bugfix] FIx torchao-config pre-commit #90935: Pull request #34430 synchronize by jwpark33
3m 34s jwpark33:hf-overrides-file
jwpark33:hf-overrides-file
3m 34s
[ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update ait… pre-commit #90934: Commit 8a798be pushed by vllm-bot
3m 55s main
main
3m 55s
[ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update ait… macOS Apple Silicon Smoke Test #2467: Commit 8a798be pushed by vllm-bot
18m 28s main
main
18m 28s
Push on main CodeQL #14375: by vllm-bot
4m 56s main
main
4m 56s
Add config file for fused MoE for Nemotron (TP4, B200) Add label on auto-merge enabled #8164: Pull request #34411 auto_merge_enabled by mgoin
10s
10s
[V0 Deprecation] Remove code related to per-request logits processors… macOS Apple Silicon Smoke Test #2466: Commit fb455ed pushed by DarkLight1337
18m 38s main
main
18m 38s