Skip to content

Actions: EricLBuehler/candle-vllm

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
412 workflow runs
412 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
Remove rust config for CI build release #2: Commit 8c34057 pushed by guoqingbao
1h 22m 54s v0.8.3
v0.8.3
1h 22m 54s
Remove rust config for CI build .github/workflows/ci.yml #844: Commit 8c34057 pushed by guoqingbao
Failure master
master
Failure
Improve kvcache allocation & model precision, add CI workflow (#430) release #1: Commit 4a7fa9e pushed by guoqingbao
16m 19s v0.8.3
v0.8.3
16m 19s
Improve kvcache allocation & model precision, add CI workflow (#430) .github/workflows/ci.yml #842: Commit 4a7fa9e pushed by guoqingbao
Failure master
master
Failure
Improve robustness of multirank inference (#428) .github/workflows/ci.yml #840: Commit 6f4b87f pushed by guoqingbao
Failure master
master
Failure
Fix Qwen3.5/3.6 GGUF precision & ISQ model path (#427) .github/workflows/ci.yml #839: Commit e82bc01 pushed by guoqingbao
Failure master
master
Failure
Optimize CUDA graph (#426) .github/workflows/ci.yml #838: Commit 76c2abe pushed by guoqingbao
Failure master
master
Failure
Improve ChatUI (smooth and fast response) .github/workflows/ci.yml #837: Commit 185caf0 pushed by guoqingbao
Failure master
master
Failure
Support quantized kvcache (#425) .github/workflows/ci.yml #836: Commit 8cb03bf pushed by guoqingbao
Failure master
master
Failure
Improve graph capture (#424) .github/workflows/ci.yml #835: Commit bb15a14 pushed by guoqingbao
Failure master
master
Failure
Fully support FP8 KVCache (#423) .github/workflows/ci.yml #834: Commit ae0e148 pushed by guoqingbao
Failure master
master
Failure
Fix corner case issue for prefix-cache and scheduler (#422) .github/workflows/ci.yml #833: Commit fbe6860 pushed by guoqingbao
Failure master
master
Failure
Fix scheduler issue when all mamba slots occupied (#421) .github/workflows/ci.yml #832: Commit c14b037 pushed by guoqingbao
Failure master
master
Failure
Fix image prefix cache miss (#420) .github/workflows/ci.yml #831: Commit 6e0bd12 pushed by guoqingbao
Failure master
master
Failure
Improve continuous batching (#419) .github/workflows/ci.yml #830: Commit f09e3fd pushed by guoqingbao
Failure master
master
Failure
Improve mamba cache allocation & working with xbot (#418) .github/workflows/ci.yml #829: Commit 1d23f69 pushed by guoqingbao
Failure master
master
Failure
Improve request admission and prefix-cache release logics (#415) .github/workflows/ci.yml #828: Commit 3b6a372 pushed by guoqingbao
Failure master
master
Failure
Send thinking process via reasoning_content for non-toolcall requests… .github/workflows/ci.yml #827: Commit 09d6d88 pushed by guoqingbao
Failure master
master
Failure
Statistics for reasoning and prefix-cached tokens (#413) .github/workflows/ci.yml #826: Commit d8786bd pushed by guoqingbao
Failure master
master
Failure
Improve prefix-cache eviction (#411) .github/workflows/ci.yml #825: Commit f3b890b pushed by guoqingbao
Failure master
master
Failure
Improve tool calling across various models (#410) .github/workflows/ci.yml #824: Commit 68c54fa pushed by guoqingbao
Failure master
master
Failure
Improve tool calling across various models .github/workflows/ci.yml #823: Pull request #410 by guoqingbao
Failure guoqingbao:master
guoqingbao:master
Failure
Typo fix (#409) .github/workflows/ci.yml #822: Commit 27bc6d1 pushed by guoqingbao
Failure master
master
Failure
Typo fix .github/workflows/ci.yml #821: Pull request #409 by guoqingbao
-1s guoqingbao:master
guoqingbao:master
-1s
Support Minimax M2.5/M2.7 models (#408) .github/workflows/ci.yml #820: Commit 769d78b pushed by guoqingbao
Failure master
master
Failure