Skip to content

Pull requests: Blaizzy/mlx-vlm

New pull request New
51 Open 612 Closed
51 Open 612 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

tests: add regression test for single Server response header
#1207 opened May 20, 2026 by funnyjas03 Loading…
5
Add config_overrides kwarg to load() and load_model()
#1204 opened May 20, 2026 by quartzjer Loading…
Modularize server
#1203 opened May 19, 2026 by lucasnewman Collaborator Loading…
Decode OpenAI input_audio base64 in chat completions
#1197 opened May 19, 2026 by Quiet-Node-io Loading…
Add RT-DETRv2 detection model
#1195 opened May 17, 2026 by leonnoirclerc Loading…
Freeze MaskedEmbedder.token_ordering so optimizer can't corrupt it
#1194 opened May 17, 2026 by DirectriX01 Loading…
@Blaizzy
fastvlm: support untied lm_head for the 7B variant
#1193 opened May 17, 2026 by contrapuntal Contributor Loading…
Fix LFM2-VL image preprocessing for variants shipping input_data_format=channels_last
#1190 opened May 16, 2026 by contrapuntal Contributor Loading…
Fix Qwen MTP verification drift and sampling parity
#1188 opened May 16, 2026 by Blaizzy Owner • Draft
Support response_format type=json_object
#1173 opened May 12, 2026 by eloe Contributor Loading…
1
Fix streaming thinking mode and tool-call content truncation
#1161 opened May 9, 2026 by jankyjames • Draft
5 tasks
1
Fix inverted --verbose flag on chat / generate / video_generate CLIs
#1152 opened May 8, 2026 by SuperMarioYL Loading…
server: populate cached_tokens and tps in usage envelope
#1151 opened May 7, 2026 by ZeroErrors Loading…
6
docs: align Python version metadata
#1150 opened May 7, 2026 by aqilaziz Loading…
3
Add TTS generation support to MiniCPM-o
#1148 opened May 7, 2026 by lucasnewman Collaborator • Draft
gemma4 mtp: demote to AR on drafter mismatch + propagate speculative errors
#1142 opened May 7, 2026 by ivanfioravanti Contributor Loading…
6 tasks done
1
Refactor MRoPE handling
#1135 opened May 7, 2026 by Blaizzy Owner • Draft
Fix TPS in API response
#1113 opened May 5, 2026 by Edsuns Loading…
2
Fix: model discovery for single-file safetensors models & improve /v1/models reporting
#1101 opened May 2, 2026 by frandariem Loading…
Add Sapiens2 + RTMDet (top-down pose pipeline)
#1081 opened Apr 26, 2026 by Blaizzy Owner Loading…
8 tasks done
Fix stale test_utils.py regressions + extract get_class_predicate
#1071 opened Apr 25, 2026 by mdstaff Contributor Loading…
2 tasks done
5
Handle OpenAI tool_choice requests
#1070 opened Apr 25, 2026 by eloe Contributor • Draft
Expose presence_penalty, frequency_penalty, and per-penalty context_size on the server API
#1023 opened Apr 14, 2026 by esaruoho Loading…
1
fix: propagate the verbose to the Prefill tqdm
#1015 opened Apr 12, 2026 by PeterStaar-IBM Loading…
1
server: indicate finish reason properly when model made a tool call.
#1014 opened Apr 12, 2026 by viktike Contributor Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.