-
Notifications
You must be signed in to change notification settings - Fork 183
Pull requests: waybarrios/vllm-mlx
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add GLM-4 reasoning parser and fix think tag / prefix cache bugs
#295
opened Apr 12, 2026 by
janhilgard
Collaborator
•
Draft
6 tasks done
Add parameter --served-model-name to vllm-mlx-chat
#292
opened Apr 12, 2026 by
perry2of5
Contributor
Loading…
test: add tokenizer fallback regression coverage
#287
opened Apr 11, 2026 by
Thump604
Collaborator
Loading…
fix: handle 3D KV tensors in prefix cache
#286
opened Apr 11, 2026 by
Thump604
Collaborator
Loading…
fix: graceful fallback when model has no chat_template (MedGemma)
#271
opened Apr 9, 2026 by
jackneil
Contributor
Loading…
2 of 3 tasks
feat: add --compile flag for mx.compile model optimization
#270
opened Apr 9, 2026 by
jackneil
Contributor
Loading…
3 tasks done
Preserve raw chat output for reasoning parsing
#255
opened Apr 5, 2026 by
Thump604
Collaborator
Loading…
fix: replace manual decode loop with pipelined generation in SpecPrefill Phase 4
#248
opened Apr 2, 2026 by
Vigilans
Loading…
3 tasks done
fix: overhaul GLM-4.7-Flash streaming tool calls and add GLM4 reasoning parser
#246
opened Apr 2, 2026 by
b2ornot2b
Loading…
fix: MLLM scheduler streaming detokenizer + VLM model pre-detection
#242
opened Mar 31, 2026 by
Thump604
Collaborator
Loading…
4 tasks
Add TurboQuant KV cache compression for prefix cache (4.6x)
#233
opened Mar 29, 2026 by
arozanov
Loading…
9 tasks done
test: make Python 3.13 async suite pass and cover it in CI
#226
opened Mar 25, 2026 by
krystophny
Contributor
Loading…
chat: forward chat_template_kwargs on simple-engine paths
#218
opened Mar 24, 2026 by
krystophny
Contributor
Loading…
server: add OpenAI-compatible /v1/responses endpoint
#214
opened Mar 24, 2026 by
krystophny
Contributor
Loading…
feat: add lifecycle-managed residency for the default server model
#205
opened Mar 22, 2026 by
lyonsno
Loading…
Fix cross-request data leakage from base64 image cache collision
#126
opened Feb 28, 2026 by
sooth
Loading…
1 of 2 tasks
feat(server): implement sequential reasoning and tool-call parsing bridge
#118
opened Feb 26, 2026 by
jonharris0n
Loading…
feat: Reasoning parser fix + jump-forward tool logits bias
#114
opened Feb 25, 2026 by
raullenchai
Loading…
4 tasks done
ProTip!
Updated in the last three days: updated:>2026-04-09.