Skip to content

Pull requests: waybarrios/vllm-mlx

New pull request New
20 Open 51 Closed
20 Open 51 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: Reasoning parser fix + jump-forward tool logits bias
#114 opened Feb 25, 2026 by raullenchai Loading…
4 tasks done
fix: Use streaming detokenizer for UTF-8-safe incremental decode
#109 opened Feb 24, 2026 by janhilgard Loading…
1 of 4 tasks
feat: Add --gpu-memory-utilization for configurable memory limits
#108 opened Feb 23, 2026 by janhilgard Loading…
5 tasks
feat: add --prefill-step-size CLI flag enhancement New feature or request
#105 opened Feb 23, 2026 by kol22 Loading…
@waybarrios @janhilgard
4
feat: Add MiniMax-M2 tool call parser
#98 opened Feb 18, 2026 by janhilgard Loading…
6 tasks done
1
fix: Disable MambaCache monkey-patch for hybrid models, add MTP auto-injection
#97 opened Feb 18, 2026 by janhilgard Loading…
3 of 5 tasks
fix: Coerce tool call arguments to match schema types
#95 opened Feb 16, 2026 by janhilgard Loading…
5 tasks
Add Step 3.5 Flash model support with MTP
#94 opened Feb 16, 2026 by janhilgard Loading…
4 tasks
Fix streaming tool calls when reasoning parser is active
#93 opened Feb 16, 2026 by janhilgard Loading…
5 tasks done
Fix Metal resource leak under high concurrency
#92 opened Feb 16, 2026 by janhilgard Loading…
4 tasks
1
feat: add prompt prefix caching to SimpleEngine enhancement New feature or request
#90 opened Feb 15, 2026 by panbanda Loading…
7 tasks done
@waybarrios
1
feat: per-request thinking/reasoning control
#85 opened Feb 15, 2026 by janhilgard Loading…
8 tasks
Add Metal memory stats to MLLMScheduler
#78 opened Feb 12, 2026 by janhilgard Loading…
1 of 2 tasks
Add resumable model download with retry, timeout, and offline mode
#77 opened Feb 12, 2026 by janhilgard Loading…
4 tasks done
2
Refactor: review improvements for KV cache quantization
#72 opened Feb 11, 2026 by janhilgard Loading…
3 tasks done
3
Security hardening: fix auth bypass, SSRF, MCP vulnerabilities (issue #68)
#70 opened Feb 11, 2026 by janhilgard Loading…
7 tasks
1
feat: repetition detector for degenerate token loops
#65 opened Feb 11, 2026 by janhilgard Loading…
1 of 3 tasks
2
fix: MLLM vision models hallucinate and ignore instructions in BatchedEngine
#54 opened Feb 9, 2026 by janhilgard Loading…
8 tasks done
Add MiniMax M2.1 tool call parser
#51 opened Feb 9, 2026 by janhilgard Loading…
3 of 4 tasks
1
feat: Add speculative decoding support with draft models
#45 opened Feb 5, 2026 by janhilgard Loading…
7 tasks done
12
ProTip! Exclude everything labeled bug with -label:bug.