Skip to content

Actions: foldl/chatllm.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
133 workflow runs
133 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix usage of QKNormedRoPEAttention CI #138: Commit 8a5018e pushed by foldl
1h 17m 37s master
master
1h 17m 37s
support penguin-vl. upload models. CI #137: Commit 366e800 pushed by foldl
1h 9m 1s master
master
1h 9m 1s
dots.ocr: fix template, use gpu. upload 1.5. CI #136: Commit 5581533 pushed by foldl
37m 49s master
master
37m 49s
save ram: qwen3.5 & mla support f16 cache and new -Os option CI #135: Commit 4eeb456 pushed by foldl
42m 21s master
master
42m 21s
torch.jit: runnable, but still slow. CI #134: Commit 8ca8acc pushed by foldl
3m 1s master
master
3m 1s
work on qwen3.5-moe (in progress); upload models CI #133: Commit 18f685f pushed by foldl
38m 50s master
master
38m 50s
work on qwen3.5-moe (in progress); upload models CI #132: Commit ca87e3d pushed by foldl
1h 7m 26s master
master
1h 7m 26s
support glm-ocr CI #131: Commit 13a4744 pushed by foldl
1h 7m 41s master
master
1h 7m 41s
fix CI and polish support of qwen2-vl CI #130: Commit 4e9bc2c pushed by foldl
19m 8s master
master
19m 8s
support youtu-vl CI #129: Commit b3580e3 pushed by foldl
21m 57s master
master
21m 57s
support youtu CI #128: Commit 75958f7 pushed by foldl
1h 6m 36s master
master
1h 6m 36s
minor update of qwen3-tts. upload models. CI #127: Commit 44eda65 pushed by foldl
17m 57s master
master
17m 57s
qwen3-tts: voice clone (xvec mode) CI #126: Commit 8b4b7d4 pushed by foldl
23m 21s master
master
23m 21s
dealing with empty "sentence" CI #125: Commit 397d3a5 pushed by foldl
1h 8m 40s master
master
1h 8m 40s
fix(memory): eliminate memory leaks in Python bindings and inference pipeline CI #124: Pull request #115 opened by vieenrose
1h 6m 2s vieenrose:fix/memory-leaks-python-bindings
vieenrose:fix/memory-leaks-python-bindings
1h 6m 2s
fix for GCC CI #119: Commit fb0c540 pushed by foldl
18m 36s master
master
18m 36s
support qwen3-tts CI #118: Commit 4f4ca5c pushed by foldl
1h 6m 11s master
master
1h 6m 11s
support ASR models in bindings CI #117: Commit cdb65fe pushed by foldl
1h 8m 20s master
master
1h 8m 20s
support Qwen3-ForceAligner CI #116: Commit d414c63 pushed by foldl
19m 54s master
master
19m 54s
bring back RPC: delayed registering of devices. CI #115: Commit 1c6a067 pushed by foldl
18m 52s master
master
18m 52s
support qwen3-asr & upload models CI #114: Commit a22839b pushed by foldl
1h 6m 45s master
master
1h 6m 45s
add pan-and-scan to step3-vl; upload models CI #113: Commit f85eb5b pushed by foldl
18m 57s master
master
18m 57s
add step-vl (only thumb image is used) CI #112: Commit 01763a6 pushed by foldl
21m 7s master
master
21m 7s
fix performance of glm-4.7-flash: score func & gating settings CI #111: Commit b9a742d pushed by foldl
19m 15s master
master
19m 15s
polish the support of translategemma, and models uploaded. CI #110: Commit a318d80 pushed by foldl
20m 36s master
master
20m 36s