Skip to content

Actions: adrianhoehne/llama.cpp

Actions

Publish CUDA Docker image

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
docker.yml
33 workflow runs
33 workflow runs

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
Update README with CUDA configuration examples Publish CUDA Docker image #33: Commit 51a54a0 pushed by adrianhoehne
1h 41m 50s cached-experts-v2
cached-experts-v2
1h 41m 50s
test: make hot-cache planner env setup portable Publish CUDA Docker image #32: Commit ef918cb pushed by adrianhoehne
1h 36m 18s cached-experts-v2
cached-experts-v2
1h 36m 18s
ci: remove stale cpu workflow dependency Publish CUDA Docker image #31: Commit 89a26f6 pushed by adrianhoehne
3m 15s cached-experts-v2
cached-experts-v2
3m 15s
fix(moe-hot-cache): bridge single-lane even-split outputs Publish CUDA Docker image #30: Commit 2e27d36 pushed by adrianhoehne
1h 37m 23s cached-experts-v2
cached-experts-v2
1h 37m 23s
feat: add auto-learn mode to replace it with the first run collection Publish CUDA Docker image #29: Commit 04c1003 pushed by adrianhoehne
1h 31m 56s cached-experts-v2
cached-experts-v2
1h 31m 56s
feat: add warmup prompt setting. Publish CUDA Docker image #28: Commit 8db1e50 pushed by adrianhoehne
1h 34m 22s cached-experts-v2
cached-experts-v2
1h 34m 22s
feat: add even-split mode to multigpu scenarios and make autofill def… Publish CUDA Docker image #27: Commit 24fdde1 pushed by adrianhoehne
33m 22s cached-experts-v2
cached-experts-v2
33m 22s
Update Readme Publish CUDA Docker image #26: Commit 6319902 pushed by adrianhoehne
1h 37m 2s cached-experts-v2
cached-experts-v2
1h 37m 2s
Update Readme Publish CUDA Docker image #25: Commit 43adabb pushed by adrianhoehne
1h 12m 33s cached-experts-v2
cached-experts-v2
1h 12m 33s
feat(moe-hot-cache): enable dense PP for supported MoE adapters Publish CUDA Docker image #24: Commit bc106d7 pushed by adrianhoehne
1h 34m 24s cached-experts-v2
cached-experts-v2
1h 34m 24s
feat: add glm moe support Publish CUDA Docker image #23: Commit 8ce1fbb pushed by adrianhoehne
1h 38m 19s cached-experts-v2
cached-experts-v2
1h 38m 19s
feat: add glm moe support Publish CUDA Docker image #22: Commit 79dd0a9 pushed by adrianhoehne
1h 35m 15s cached-experts-v2
cached-experts-v2
1h 35m 15s
fix: guard GPT-OSS multi-lane hot-cache to decode token only Publish CUDA Docker image #21: Commit 1c4fed6 pushed by adrianhoehne
1h 34m 44s cached-experts-v2
cached-experts-v2
1h 34m 44s
add gpt-oss support v1 Publish CUDA Docker image #20: Commit e072167 pushed by adrianhoehne
1h 40m 58s cached-experts-v2
cached-experts-v2
1h 40m 58s
feat: Add multi-GPU MoE hot-cache expert lanes Publish CUDA Docker image #19: Commit f151200 pushed by adrianhoehne
1h 0m 40s cached-experts-v2
cached-experts-v2
1h 0m 40s
feat: Add hot-cache implementation on top of upstream mellum2 support… Publish CUDA Docker image #18: Commit 4926649 pushed by adrianhoehne
1h 25m 8s cached-experts-v2
cached-experts-v2
1h 25m 8s
feat: Add hot-cache implementation on top of upstream mellum2 support… Publish CUDA Docker image #17: Commit 5bdda1c pushed by adrianhoehne
1h 31m 54s cached-experts-v2
cached-experts-v2
1h 31m 54s
Merge upstream_update into cached-experts-v2 Publish CUDA Docker image #16: Commit bcaad94 pushed by adrianhoehne
1h 33m 17s cached-experts-v2
cached-experts-v2
1h 33m 17s
feat: Add mellum2 to hot-cache Publish CUDA Docker image #15: Commit ef2c316 pushed by adrianhoehne
1h 36m 19s cached-experts-v2
cached-experts-v2
1h 36m 19s
feat: Save perf to disk, backup old perf and replace actual perf Publish CUDA Docker image #14: Commit 894abfc pushed by adrianhoehne
1h 27m 5s cached-experts-v2
cached-experts-v2
1h 27m 5s
Exchange perf (#3) Publish CUDA Docker image #13: Commit affaffa pushed by adrianhoehne
1h 36m 29s cached-experts-v2
cached-experts-v2
1h 36m 29s
Save perf as (#2) Publish CUDA Docker image #12: Commit bcfdd29 pushed by adrianhoehne
1h 28m 29s cached-experts-v2
cached-experts-v2
1h 28m 29s
ci : releases use Github-hosted builds for the UI (#23823) Publish CUDA Docker image #11: Commit 3de8a20 pushed by adrianhoehne
1h 26m 0s cached-experts-v2
cached-experts-v2
1h 26m 0s
ui: fix audio and video modality detection (#23756) Publish CUDA Docker image #10: Commit 9f33501 pushed by adrianhoehne
52m 17s cached-experts-v2
cached-experts-v2
52m 17s
Document and refine MoE hot-cache PP optimization path (#1) Publish CUDA Docker image #9: Commit 5afe2f7 pushed by adrianhoehne
1h 27m 25s cached-experts-v2
cached-experts-v2
1h 27m 25s