Skip to content

Actions: leejet/stable-diffusion.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,222 workflow runs
2,222 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
feat: support building with upstream ggml (#1999) CI #3179: Commit 1330ceb pushed by leejet
2h 34m 9s master
master
2h 34m 9s
feat: support building with upstream ggml CI #3178: Pull request #1999 opened by leejet
2h 48m 36s feat/support-upstream-ggml
feat/support-upstream-ggml
2h 48m 36s
perf: parallelize host tensor elementwise and broadcast ops (#1998) CI #3177: Commit 17860c0 pushed by leejet
2h 13m 19s master
master
2h 13m 19s
perf: parallelize host tensor elementwise and broadcast ops CI #3176: Pull request #1998 opened by leejet
2h 36m 20s perf/parallelize-host-tensor-ops
perf/parallelize-host-tensor-ops
2h 36m 20s
perf: reduce CPU overhead in graph execution and sampling (#1997) CI #3175: Commit 275ab58 pushed by leejet
6h 52m 12s master
master
6h 52m 12s
fix: prevent clip_preprocess center crop from exceeding the resized i… CI #3174: Commit d32b4e8 pushed by leejet
3h 6m 53s master
master
3h 6m 53s
fix: propagate CUDA driver dependency to shared library consumers CI #3173: Commit 9982c9c pushed by leejet
6h 9m 31s master
master
6h 9m 31s
perf: reduce CPU overhead in graph execution and sampling CI #3172: Pull request #1997 opened by leejet
2h 22m 50s perf/reduce-sampling-cpu-overhead
perf/reduce-sampling-cpu-overhead
2h 22m 50s
perf: accelerate VAE direct 3D convolutions (#1996) CI #3171: Commit 3e037a8 pushed by leejet
2h 49m 23s master
master
2h 49m 23s
perf: accelerate VAE direct 3D convolutions CI #3170: Pull request #1996 opened by leejet
2h 49m 11s perf/ggml-implicit-gemm-conv3d
perf/ggml-implicit-gemm-conv3d
2h 49m 11s
Close inactive PRs Close inactive PRs #127: Scheduled
10s master
master
10s
Close inactive issues Close inactive issues #74: Scheduled
14s master
master
14s
fix: prevent clip_preprocess center crop from exceeding the resized image CI #3169: Pull request #1995 synchronize by akhenakh
2h 49m 58s akhenakh:fix/clip-preprocess-resize-rounding
akhenakh:fix/clip-preprocess-resize-rounding
2h 49m 58s
fix: prevent clip_preprocess center crop from exceeding the resized image CI #3168: Pull request #1995 opened by akhenakh
2h 43m 21s akhenakh:fix/clip-preprocess-resize-rounding
akhenakh:fix/clip-preprocess-resize-rounding
2h 43m 21s
feat: add Qwen Image 2.1 support CI #3167: Pull request #1994 opened by leejet
2h 47m 25s feat/qwen-image-2-1
feat/qwen-image-2-1
2h 47m 25s
perf: update ggml for faster direct convolutions (#1993) CI #3166: Commit 2ea8aff pushed by leejet
2h 36m 19s master
master
2h 36m 19s
perf: update ggml for faster direct convolutions CI #3165: Pull request #1993 opened by leejet
2h 48m 9s perf/ggml-implicit-gemm-conv2d
perf/ggml-implicit-gemm-conv2d
2h 48m 9s
perf: pad small attention heads to 64 for MMA Flash Attention (#1992) CI #3164: Commit adcac69 pushed by leejet
2h 50m 52s master
master
2h 50m 52s
perf: pad small attention heads to 64 for MMA Flash Attention CI #3163: Pull request #1992 opened by leejet
2h 52m 38s perf/cuda-fa-head-padding
perf/cuda-fa-head-padding
2h 52m 38s
refactor: remove obsolete unused tensor filtering (#1984) CI #3162: Commit 656a135 pushed by leejet
3h 3m 46s master
master
3h 3m 46s
fix: honor flash attention flag in LLM text encoder attention (#1987) CI #3161: Commit 269e726 pushed by leejet
10m 41s master
master
10m 41s
Close inactive PRs Close inactive PRs #126: Scheduled
8s master
master
8s
Close inactive issues Close inactive issues #73: Scheduled
11s master
master
11s
fix: honor flash attention flag in LLM text encoder attention CI #3160: Pull request #1987 opened by linxuhao
10m 31s linxuhao:fix/llm-flash-attention
linxuhao:fix/llm-flash-attention
10m 31s
Close inactive PRs Close inactive PRs #125: Scheduled
11s master
master
11s