Skip to content

Pull requests: Blaizzy/mlx-vlm

New pull request New
36 Open 902 Closed
36 Open 902 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

Improve generation API type hints codex codex-automation
#1599 opened Jul 15, 2026 by Blaizzy Owner Loading…
1
fix(apc): exact hybrid + TurboQuant warm match live kv layout
#1596 opened Jul 14, 2026 by weklund Contributor Loading…
4 of 5 tasks
1
Fix ResponseGenerator cross-thread preprocessing arrays codex codex-automation
#1595 opened Jul 14, 2026 by Blaizzy Owner • Draft
1
Add decoder_input_ids warm start for DiffusionGemma
#1589 opened Jul 13, 2026 by Blaizzy Owner • Draft
1
perf(qwen3_5): add exact 8-bit MTP verification
#1577 opened Jul 11, 2026 by bold84 • Draft
feat(apc): APC_EXACT_MAX_PROMPT_TOKENS — cap prompt length eligible for exact-store
#1576 opened Jul 11, 2026 by pinglin Loading…
fix(apc): validate runtime caches and trace block stores
#1573 opened Jul 11, 2026 by Blaizzy Owner • Draft
add glm4_moe_lite_mtp drafter (GLM-4.7-Flash MTP split tool)
#1570 opened Jul 11, 2026 by samithaj Loading…
Add YaRN support to MRoPE rotary embeddings
#1479 opened Jul 2, 2026 by FinnTheClaw Loading…
1
5
feat(dspark): DeepSeek-V4 Flash/Pro DSpark self-speculative drafter
#1468 opened Jun 30, 2026 by popfido Contributor Loading…
3 of 4 tasks
feat: Gemma 4 DSpark self-speculative decoding
#1465 opened Jun 29, 2026 by popfido Contributor Loading…
11
[codex] Skip read-only generation config defaults codex codex-automation
#1457 opened Jun 27, 2026 by Blaizzy Owner • Draft
Add PP-OCRv6 model support
#1420 opened Jun 23, 2026 by mikolaj92 Loading…
2
Fix SAM 3.1 interactive point/box segmentation (prompt-insensitive noise)
#1409 opened Jun 19, 2026 by FAbrahamDev • Draft
[codex] Skip read-only generation config defaults codex codex-automation
#1399 opened Jun 19, 2026 by Blaizzy Owner • Draft
fix(qwen3_omni): pass decoded audio arrays to the processor, not raw paths/BytesIO
#1352 opened Jun 11, 2026 by DoradusResearch Loading…
Add CoPE (Clipped RoPE) soft-clipping for zero-shot context extension
#1344 opened Jun 10, 2026 by machiabeli Loading…
4
Add MLX-VLM agent skills
#1343 opened Jun 10, 2026 by Blaizzy Owner Loading…
Add local client setup command
#1341 opened Jun 9, 2026 by Blaizzy Owner Loading…
Fix MTP server target model handling codex
#1319 opened Jun 7, 2026 by Blaizzy Owner Loading…
1
Port Nemotron H ModelOpt weights
#1314 opened Jun 6, 2026 by Blaizzy Owner Loading…
Add RealtimeSession: incremental audio for realtime interaction
#1289 opened Jun 4, 2026 by fum0passiv0 Loading…
feat(mla): FP8 KV cache for MLA models with absorbed-decode Metal kernel
#1284 opened Jun 4, 2026 by popfido Contributor Loading…
4
Add config_overrides kwarg to load() and load_model() needs-repro type/feature
#1204 opened May 20, 2026 by quartzjer Loading…
@Blaizzy
Add TTS generation support to MiniCPM-o
#1148 opened May 7, 2026 by lucasnewman Collaborator Loading…
7
ProTip! Type g i on any issue or pull request to go back to the issue listing page.