Workflow runs · EvolvingLMMs-Lab/lmms-eval · GitHub

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows

3,277 workflow runs

3,277 workflow runs

[Bug / Design] serve mode loses 3D RoPE temporal encoding for Qwen3-VL Claude Code #1088: Issue #1266 opened by Tohrusky

2s

2s

[Bug] vLLM backend crashes with "top_p must be in (0, 1]" when task config sets top_p=0 Claude Code #1087: Issue #1265 opened by songyuc

1s

1s

add Qwen 3.5 chat model and example Lint #3061: Pull request #1264 synchronize by ArdalanM

58s ArdalanM:feat_add_qwen35_chat

ArdalanM:feat_add_qwen35_chat

58s

add Qwen 3.5 chat model and example Lint #3060: Pull request #1264 opened by ArdalanM

57s ArdalanM:feat_add_qwen35_chat

ArdalanM:feat_add_qwen35_chat

57s

feat: add MiniMax as LLM judge provider Lint #3059: Pull request #1263 opened by octo-patch

Action required octo-patch:feature/add-minimax-provider

octo-patch:feature/add-minimax-provider

Action required

feat: add PushUpBench video repetition counting benchmark task-input-ab #93: Pull request #1262 opened by anonymous-atom

Action required anonymous-atom:pushupbench

anonymous-atom:pushupbench

Action required

feat: add PushUpBench video repetition counting benchmark Lint #3058: Pull request #1262 opened by anonymous-atom

Action required anonymous-atom:pushupbench

anonymous-atom:pushupbench

Action required

Fix missing video_metadata argument in qwen2.5-vl processor forward path Lint #3057: Pull request #1261 synchronize by akawincent

56s akawincent:codex/qwen25vl-video-metadata

akawincent:codex/qwen25vl-video-metadata

56s

Fix missing video_metadata argument in qwen2.5-vl processor forward path Lint #3056: Pull request #1261 opened by akawincent

54s akawincent:codex/qwen25vl-video-metadata

akawincent:codex/qwen25vl-video-metadata

54s

Fix missing VideoReader imports in FALCONBench and LongVideoBench Lint #3055: Pull request #1258 synchronize by akawincent

52s akawincent:pr

52s

Fix missing VideoReader imports in FALCONBench and LongVideoBench task-input-ab #92: Pull request #1258 synchronize by akawincent

2m 14s akawincent:pr

2m 14s

Fix missing VideoReader imports in FALCONBench and LongVideoBench Lint #3054: Pull request #1258 synchronize by akawincent

50s akawincent:pr

50s

Fix missing VideoReader imports in FALCONBench and LongVideoBench task-input-ab #91: Pull request #1258 synchronize by akawincent

2m 20s akawincent:pr

2m 20s

[Bug] qwen2_5_vl drops sampled video metadata before processor, which silently corrupts second_per_grid_ts Claude Code #1086: Issue #1260 opened by akawincent

2s

2s

Decouple reasoning and evaluation Claude Code #1085: Issue #1259 opened by xuzhang0112

3s

3s

Fix missing VideoReader imports in FALCONBench and LongVideoBench Lint #3053: Pull request #1258 opened by akawincent

57s akawincent:pr

57s

Fix missing VideoReader imports in FALCONBench and LongVideoBench task-input-ab #90: Pull request #1258 opened by akawincent

2m 9s akawincent:pr

2m 9s

muirbench 的结果比官方低了很多是怎么回事呢 Claude Code #1084: Issue comment #805 (comment) created by yaoyaolove

2s

2s

muirbench 的结果比官方低了很多是怎么回事呢 Claude Code #1083: Issue comment #805 (comment) created by yaoyaolove

1s

1s

muirbench 的结果比官方低了很多是怎么回事呢 Claude Code #1082: Issue comment #805 (comment) created by mathCrazyy

1s

1s

muirbench 的结果比官方低了很多是怎么回事呢 Claude Code #1081: Issue comment #805 (comment) created by yaoyaolove

2s

2s

feat: add Qwen3.5 model implementation and registration Claude Code #1080: Issue comment #1249 (comment) created by Artessay

Skipped

Skipped

Feat: add model support for penguinvl task-input-ab #89: Pull request #1257 opened by taintaintainu

2m 8s taintaintainu:feat/add-model-penguinvl

taintaintainu:feat/add-model-penguinvl

2m 8s

Feat: add model support for penguinvl Lint #3052: Pull request #1257 opened by taintaintainu

54s taintaintainu:feat/add-model-penguinvl

taintaintainu:feat/add-model-penguinvl

54s

muirbench 的结果比官方低了很多是怎么回事呢 Claude Code #1079: Issue comment #805 (comment) created by mathCrazyy

2s

2s