Skip to content

Pull requests: waybarrios/vllm-mlx

New pull request New
20 Open 425 Closed
20 Open 425 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

fix: detach stored prefix-cache entries from live batch state
#642 opened Jul 22, 2026 by rohnach29 Loading…
1
feat(registry): add CLI override for memory budget
#640 opened Jul 16, 2026 by icarus0adios-netizen Loading…
@waybarrios
fix(registry): honor auto-unload-idle-seconds and release MLX memory on unload
#638 opened Jul 15, 2026 by brandy975 Loading…
1
Fix fail-open structured-output enforcement
#636 opened Jul 13, 2026 by Thump604 Collaborator Loading…
1
@janhilgard
fix(engine): close SSD cache tier on stop paths
#634 opened Jul 11, 2026 by djacobsmeyer Loading…
fix(deps): exclude corrupt mlx-vlm 0.6.4 release
#633 opened Jul 10, 2026 by Thump604 Collaborator Loading…
Fix Mistral tool parser for the [ARGS]-marker format (Ministral 3, Devstral Small 2)
#631 opened Jul 6, 2026 by mabaeyens Loading…
3 tasks done
@waybarrios
1
Add MseeP.ai badge
#630 opened Jul 6, 2026 by mseep-ai Loading…
fix(simple-engine): stamp finish_reason="stop" on natural-stop streaming epilogue
#629 opened Jul 3, 2026 by mvmories Loading…
1
fix(embeddings,rerank): resolve truncation length from model config instead of hardcoded 512
#626 opened Jul 2, 2026 by brandy975 Loading…
1
fix(engine): stop MLLM text route at the model's full config EOS set
#610 opened Jun 11, 2026 by ursk Contributor Loading…
4
fix(step): add Step3p5 parser support
#598 opened Jun 6, 2026 by Thump604 Collaborator Loading…
@janhilgard
1
fix(llama-tool-parser): recognize Llama 3.1+ / 3.3 tool-call formats
#580 opened May 25, 2026 by CBribiescas Contributor Loading…
3
Add SimpleEngine prefix trie cache
#574 opened May 24, 2026 by Thump604 Collaborator Loading…
@waybarrios @janhilgard
1
fix(gpt-oss): plumb harmony tool calls all the way through to response
#562 opened May 22, 2026 by CBribiescas Contributor Loading…
3 tasks
3
Reduce EngineCore idle polling
#552 opened May 20, 2026 by Thump604 Collaborator Loading…
@waybarrios @janhilgard
1
Keep MLLM media stream on owner thread
#551 opened May 19, 2026 by Thump604 Collaborator Loading…
@waybarrios @janhilgard
1
Keep VLM TextModel generation on owner thread
#543 opened May 17, 2026 by Thump604 Collaborator Loading…
@waybarrios @janhilgard
fix: Qwen tool streaming recovery
#497 opened May 4, 2026 by kylejeske Loading…
15
perf: O(1) tool lookup in ToolExecutor via lazily-cached name index optimization
#449 opened Apr 26, 2026 by clickbrain Contributor Loading…
@waybarrios
6
ProTip! Filter pull requests by the default branch with base:main.