Skip to content

Pull requests: eloe/mlx-vlm

New pull request New
10 Open 1 Closed
10 Open 1 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat: add request cancellation and timeout support
#20 opened Apr 6, 2026 by eloe Owner Loading…
12
feat: add --max-context-tokens for OOM prevention
#19 opened Apr 6, 2026 by eloe Owner Loading…
3
feat: add JSON mode via response_format parameter
#18 opened Apr 6, 2026 by eloe Owner Loading…
9
feat: add logprobs support to /chat/completions
#17 opened Apr 6, 2026 by eloe Owner Loading…
4
feat: enforce tool_choice parameter in chat/completions
#16 opened Apr 6, 2026 by eloe Owner Loading…
6
feat: add stop sequences support for both endpoints
#15 opened Apr 6, 2026 by eloe Owner Loading…
7
fix: return finish_reason=tool_calls when tool calls detected
#14 opened Apr 6, 2026 by eloe Owner Loading…
3
feat: concurrency guard for Metal GPU serialization
#13 opened Apr 6, 2026 by eloe Owner Loading…
5
feat: prompt prefix caching for server endpoints
#12 opened Apr 6, 2026 by eloe Owner Loading…
11
feat: OpenAI Responses API compliance with structured tool calling
#11 opened Apr 6, 2026 by eloe Owner Loading…
6
ProTip! no:milestone will show everything without a milestone.