Skip to content

Actions: Quozul/llama_cpp_router

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
32 workflow runs
32 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: add new settings to improve perf for agentic workloads CI #24: Commit 84d3326 pushed by Quozul
22s master
master
22s
feat: add cont batching, parallel and reasoning effort CI #23: Commit cbcfe3e pushed by Quozul
18s master
master
18s
feat: add cont batching, parallel and reasoning effort CI #22: Commit 954a165 pushed by Quozul
13s master
master
13s
feat: add open ai responses controller CI #21: Commit a09a41b pushed by Quozul
14s master
master
14s
feat: Add support for unified memory CI #20: Commit 554fa38 pushed by Quozul
15s master
master
15s
fix: Cancel request if aborted before model is loaded CI #19: Commit 6eede0d pushed by Quozul
15s master
master
15s
fix: Prevent same model from being loaded twice CI #18: Commit 8ee67a1 pushed by Quozul
14s master
master
14s
feat: Add new llama.cpp completion controller CI #17: Commit 22deaf4 pushed by Quozul
21s master
master
21s
fix: Add maximum concurrent model count CI #16: Commit fb40bf1 pushed by Quozul
21s master
master
21s
chore(docs): Update README CI #15: Commit 6c66f93 pushed by Quozul
17s master
master
17s
feat: Add endpoint to get and update the current config CI #14: Commit 854ea25 pushed by Quozul
23s master
master
23s
fix: Missing content type for non streaming responses CI #13: Commit 841cdd0 pushed by Quozul
18s master
master
18s
fix: Missing content type for non streaming responses CI #12: Commit 7782d46 pushed by Quozul
37s master
master
37s
feat: Config argument CI #11: Commit f5cfe56 pushed by Quozul
16s master
master
16s
feat: Support for embeddings CI #10: Commit 04b59f4 pushed by Quozul
20s master
master
20s
feat: Implement logic to proxy OpenAI chat requests CI #9: Commit 75253bf pushed by Quozul
20s master
master
20s
feat: Implement logic to proxy OpenAI chat requests CI #8: Commit 71d58e7 pushed by Quozul
22s master
master
22s
feat: Implement logic to proxy OpenAI chat requests CI #7: Commit 65e55fc pushed by Quozul
16s master
master
16s
feat: Implement logic to proxy OpenAI chat requests CI #6: Commit f8ecdd5 pushed by Quozul
20s master
master
20s
feat: Implement logic to proxy OpenAI chat requests CI #5: Commit 48b88d7 pushed by Quozul
19s master
master
19s
feat: Implement logic to proxy OpenAI chat requests CI #4: Commit 5868e98 pushed by Quozul
14s master
master
14s
feat: Implement logic to proxy OpenAI chat requests CI #3: Commit 6dd1f39 pushed by Quozul
20s master
master
20s
feat: Implement logic to proxy OpenAI chat requests CI #2: Commit 80e17f1 pushed by Quozul
12s master
master
12s
fix: prevent unloading active model Create and publish a Docker image #10: Commit ecc39e9 pushed by Quozul
1m 48s master
master
1m 48s
fix: remove message from completion request Create and publish a Docker image #9: Commit 28f7b6e pushed by Quozul
1m 48s master
master
1m 48s