Skip to content

Pull requests: lmstudio-ai/mlx-engine

New pull request New
6 Open 152 Closed
6 Open 152 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

Qwen 3.5 Unified CLA signed Indicates that all contributors have signed
#298 opened Mar 30, 2026 by will-lms Loading…
1
GPT-OSS prompt caching fix CLA signed Indicates that all contributors have signed
#297 opened Mar 29, 2026 by dmitryryabkov Loading…
1
2
feat: support Flash Weight Streaming via mlx-flash for models larger than RAM CLA signed Indicates that all contributors have signed
#293 opened Mar 21, 2026 by matt-k-wong Loading…
4
Add mode parameter to quantization options, allowing other quantization mode to work with vision add-on. CLA signed Indicates that all contributors have signed
#271 opened Feb 8, 2026 by Foxtr0t1337 Loading…
2
[unified arch] Cache the outputs of the vision encoder CLA signed Indicates that all contributors have signed
#241 opened Oct 29, 2025 by neilmehta24 Loading…
Cache reuse and cache fixes CLA signed Indicates that all contributors have signed
#188 opened Jul 10, 2025 by christian-lms • Draft
2 tasks
1
4
ProTip! Adding no:label will show everything without a label.