Skip to content

Actions: Edge0-AI/Edge0

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
89 workflow runs
89 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
Merge pull request #124 from Edge0-AI/docs/drop-prefill-ondemand-news CI #87: Commit af5cd15 pushed by linyubupa
34s main
main
34s
docs(readme): drop the 2026-09-20 prefill-ondemand news line in all l… CI #86: Pull request #124 opened by linyubupa
44s docs/drop-prefill-ondemand-news
docs/drop-prefill-ondemand-news
44s
Merge pull request #123 from Edge0-AI/refactor/multi-platform-layout CI #85: Commit 88f121d pushed by linyubupa
31s main
main
31s
add multi-platform inference framework CI #84: Pull request #123 opened by chenbin11200
40s refactor/multi-platform-layout
refactor/multi-platform-layout
40s
Running Copilot Code Review Copilot #2: by Copilot AI
5m 37s main
main
5m 37s
backends/cuda: a torch reference backend — edge0-8b and edge0-35b generate text on an NVIDIA GPU CI #83: Pull request #19 synchronize by agourakis82
44s agourakis82:cuda-backend
agourakis82:cuda-backend
44s
fix(strip_vision_weights): shrink metadata.total_size by dropped bytes CI #82: Pull request #121 opened by kuishou68
Action required kuishou68:cocoon-fix-edge0
kuishou68:cocoon-fix-edge0
Action required
docs(streaming): document warm_willneed as inert under prod_k8() CI #81: Pull request #120 opened by agourakis82
43s agourakis82:docs/warm-willneed-inert-under-prod-k8
agourakis82:docs/warm-willneed-inert-under-prod-k8
43s
feat(server): OpenAI-compatible tool/function calling CI #80: Pull request #119 opened by agourakis82
40s agourakis82:feat/openai-tool-calling
agourakis82:feat/openai-tool-calling
40s
docs(streaming): correct load_hot_layer's "page cache" backing claim CI #79: Pull request #118 opened by agourakis82
55s agourakis82:fix/hot-layer-anonymous-memory-doc
agourakis82:fix/hot-layer-anonymous-memory-doc
55s
fix(scripts): recompute metadata.total_size after stripping vision weights CI #78: Pull request #117 opened by agourakis82
44s agourakis82:fix/strip-vision-total-size
agourakis82:fix/strip-vision-total-size
44s
fix(scripts): upload README.md in upload_hf.py CI #77: Pull request #116 opened by agourakis82
35s agourakis82:fix/upload-hf-readme
agourakis82:fix/upload-hf-readme
35s
fix(streaming): stop layer discovery on IndexError too CI #76: Pull request #13 synchronize by agourakis82
42s agourakis82:fix/install-layer-discovery
agourakis82:fix/install-layer-discovery
42s
Merge pull request #112 from Edge0-AI/feat/prefill-ondemand-cli CI #75: Commit fb4cd2c pushed by linyubupa
44s main
main
44s
feat(cli): --prefill-ondemand for demo / chat / serve CI #74: Pull request #112 opened by linyubupa
36s feat/prefill-ondemand-cli
feat/prefill-ondemand-cli
36s
Merge pull request #111 from Edge0-AI/fix/8b-prefill-full-layer-noop CI #73: Commit afaf9d0 pushed by linyubupa
38s main
main
38s
fix(prefill): honor full_layer_prefill=False on the streaming engines CI #72: Pull request #111 opened by linyubupa
37s fix/8b-prefill-full-layer-noop
fix/8b-prefill-full-layer-noop
37s
tests: make the MLX boundary guard catch mlx_lm imports CI #71: Pull request #108 opened by VKVstudio
Action required VKVstudio:fix/hygiene-mlx-lm-regex
VKVstudio:fix/hygiene-mlx-lm-regex
Action required
docs(readme): add the arXiv badge next to the model links CI #70: Commit 5b65e6f pushed by linyubupa
32s main
main
32s
docs(readme): add the ModelScope mirrors next to the Hugging Face links CI #69: Commit f8c4cb2 pushed by linyubupa
36s main
main
36s
docs(paper): add Edge0 technical report (The Other Half of the Memory… CI #68: Commit ca40e7d pushed by linyubupa
47s main
main
47s
backends/cuda: a torch reference backend — edge0-8b and edge0-35b generate text on an NVIDIA GPU CI #67: Pull request #19 synchronize by agourakis82
38s agourakis82:cuda-backend
agourakis82:cuda-backend
38s
fix(server): decode streamed SSE text from the cumulative id list CI #66: Pull request #105 opened by ahrazzle
39s ahrazzle:fix/sse-incremental-decode
ahrazzle:fix/sse-incremental-decode
39s
Merge pull request #102 from linyubupa/feat/streaming-willneed-readahead CI #65: Commit c18eb62 pushed by linyubupa
51s main
main
51s
backends/cuda: a torch reference backend — edge0-8b and edge0-35b generate text on an NVIDIA GPU CI #64: Pull request #19 synchronize by agourakis82
35s agourakis82:cuda-backend
agourakis82:cuda-backend
35s