Skip to content

Actions: jundot/omlx

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
510 workflow runs
510 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
fix: use 'hermes chat' subcommand in Hermes launch integration CI #516: Pull request #1878 synchronize by fparrav
5m 46s fparrav:fix/hermes-launch-command
fparrav:fix/hermes-launch-command
5m 46s
fix: use 'hermes chat' subcommand in Hermes launch integration CI #515: Pull request #1878 opened by fparrav
6m 6s fparrav:fix/hermes-launch-command
fparrav:fix/hermes-launch-command
6m 6s
feat(api): OpenAI-compatible logprobs for /v1/chat/completions (#1549) CI #514: Pull request #1591 synchronize by popfido
6m 23s popfido:feat/openai-logprobs-1549
popfido:feat/openai-logprobs-1549
6m 23s
feat: support MiniMax M3 from in-progress mlx-vlm PR CI #513: Pull request #1875 synchronize by jundot
11m 9s feat/minimax-m3-mlx-vlm-pr
feat/minimax-m3-mlx-vlm-pr
11m 9s
fix(api): parse Gemma 4 namespaced and single-quoted tool calls CI #512: Pull request #1854 synchronize by richgoodson
5m 58s richgoodson:fix/1830-gemma4-mcp-tool-names
richgoodson:fix/1830-gemma4-mcp-tool-names
5m 58s
feat: support MiniMax M3 from in-progress mlx-vlm PR CI #511: Pull request #1875 opened by jundot
6m 9s feat/minimax-m3-mlx-vlm-pr
feat/minimax-m3-mlx-vlm-pr
6m 9s
feat(thinking): add soft thinking budget zone with progressive logit bias CI #510: Pull request #1812 synchronize by efortin
5m 39s efortin:feat/soft-thinking-budget
efortin:feat/soft-thinking-budget
5m 39s
feat(thinking): add soft thinking budget zone with progressive logit bias CI #509: Pull request #1812 synchronize by efortin
6m 22s efortin:feat/soft-thinking-budget
efortin:feat/soft-thinking-budget
6m 22s
fix: add macOS memory stats compat layer CI #508: Commit e435443 pushed by jundot
6m 7s main
main
6m 7s
fix: honor request max_tokens with force_sampling (#1857) CI #507: Commit fd327fa pushed by jundot
6m 11s main
main
6m 11s
fix(scheduler): realign rows before native MTP decode CI #506: Commit 05b079d pushed by jundot
6m 4s main
main
6m 4s
fix(scheduler): realign per-row samplers and logits processors by uid… CI #505: Commit 205a23b pushed by jundot
6m 36s main
main
6m 36s
fix(api): harden /v1/completions thinking_budget (#1821) CI #504: Commit 9b8cda5 pushed by jundot
4m 14s main
main
4m 14s
fix(api): harden /v1/completions thinking_budget (validation, stream parity, tokenizer detection) on top of #1844 CI #503: Pull request #1821 synchronize by efortin
6m 0s efortin:fix/completions-thinking-budget
efortin:fix/completions-thinking-budget
6m 0s
fix(scheduler): realign per-row samplers and logits processors by uid CI #502: Pull request #1824 synchronize by efortin
6m 17s efortin:fix/batch-row-realignment
efortin:fix/batch-row-realignment
6m 17s
chore(deps-dev): bump xgrammar from 0.2.0 to 0.2.2 CI #501: Pull request #1872 opened by dependabot Bot
11m 25s dependabot/pip/xgrammar-0.2.2
dependabot/pip/xgrammar-0.2.2
11m 25s
chore(deps-dev): bump apache-tvm-ffi from 0.1.11 to 0.1.12 CI #500: Pull request #1871 opened by dependabot Bot
6m 0s dependabot/pip/apache-tvm-ffi-0.1.12
dependabot/pip/apache-tvm-ffi-0.1.12
6m 0s
github_actions in /. - Update #1411473176 Dependabot Updates #6: by dependabot Bot
29s main
main
29s
pip in /. - Update #1411473172 Dependabot Updates #5: by dependabot Bot
1m 35s main
main
1m 35s
fix: harden TurboQuant cache eligibility (#1842) CI #499: Commit a803e62 pushed by jundot
6m 30s main
main
6m 30s
fix: stabilize TurboQuant prefix cache handling (#1842) CI #498: Commit 2cb955d pushed by jundot
10m 11s main
main
10m 11s
fix(api): parse Gemma 4 namespaced and single-quoted tool calls CI #497: Pull request #1854 synchronize by richgoodson
5m 55s richgoodson:fix/1830-gemma4-mcp-tool-names
richgoodson:fix/1830-gemma4-mcp-tool-names
5m 55s
fix: reserve hot-cache headroom in memory guard (#1833) CI #496: Commit 4458885 pushed by jundot
6m 22s main
main
6m 22s
fix: support mlx-lm 2c008fd pin CI #495: Commit 3489cf2 pushed by jundot
4m 18s main
main
4m 18s
fix: avoid hot cache growth under memory pressure (#1777) CI #494: Commit 814a687 pushed by jundot
5m 53s main
main
5m 53s