Skip to content

Pull requests: ml-explore/mlx-lm

New pull request New
232 Open 689 Closed
232 Open 689 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 Mistral tool parser dropping parallel/multiple tool calls
#1448 opened Jul 2, 2026 by DavidObando Loading…
Fix dropped tool calls for models with empty tool_call_end (Mistral/Devstral)
#1447 opened Jul 1, 2026 by DavidObando Loading…
1
Fix frozen PRNG in categorical_sampling under repeated sampling
#1444 opened Jun 30, 2026 by utkarshtiwari-24 Loading…
1
2
Fix qwen3.5-MoE garbage output: don't double-shift RMSNorm on MTP-retaining checkpoints
#1442 opened Jun 29, 2026 by embwl0x Loading…
Feature/layer streaming
#1440 opened Jun 28, 2026 by SashimiSaketoro Loading…
Make RotatingKVCache trimmable so prefix cache reuse works for sliding-window models
#1437 opened Jun 26, 2026 by amirarsalan90 Loading…
Fix: pythonic tool parser not auto-detected for LFM2.5 models
#1436 opened Jun 25, 2026 by grumdahl Loading…
fix: use FiscalNote/billsum HF dataset path in test_datsets
#1434 opened Jun 25, 2026 by ttxs69 Loading…
Add dedicated tests for AFM7 model
#1432 opened Jun 24, 2026 by Sreya8 Loading…
server: add --lazy CLI flag for deferred model loading
#1429 opened Jun 24, 2026 by cyq1017 Loading…
1
Fix speculative decode with full rotating caches
#1427 opened Jun 23, 2026 by cyq1017 Loading…
1
tests: add dedicated unit tests for Gemma3n model
#1424 opened Jun 23, 2026 by Sreya8 Loading…
feat: add batch_generate_same_prompt for SSM/hybrid models
#1422 opened Jun 21, 2026 by HaoXuAI Contributor Loading…
1
GLM-5.2 (glm_moe_dsa) inference: IndexShare, indexer RoPE/eps, int8 MLA-KV
#1419 opened Jun 21, 2026 by avlp12 Loading…
1
1
Fix: qwen3_coder drops tool calls with float-formatted integer args
#1417 opened Jun 20, 2026 by brianmeyers007 Loading…
Add MiniMax-M3 tool-call parser
#1416 opened Jun 20, 2026 by anjansastry-hash Loading…
3 tasks done
1
Add Laguna M.1 model
#1415 opened Jun 18, 2026 by eauchs Loading…
fix: merge config.json eos_token_id with tokenizer-derived value instead of replacing it
#1414 opened Jun 18, 2026 by EmreCelenli Loading…
Fix gradient accumulation to weight micro-batches by token count
#1413 opened Jun 18, 2026 by Incheonkirin Loading…
Support per-layer DSA indexer schedule (GLM-5.2)
#1412 opened Jun 17, 2026 by davidrhodus Loading…
[transformers-to-mlx skill] glm_moe_dsa: DSA cross-layer indexer sharing (GLM-5.2)
#1410 opened Jun 16, 2026 by pcuenca Contributor • Draft
15
fix(server): reduce prompt cache memory pressure
#1409 opened Jun 16, 2026 by jsiu93 Loading…
1
fix(server): build xtc_special_tokens as a flat list
#1408 opened Jun 15, 2026 by devYRPauli Contributor Loading…
Add Quasar-Long (silx-ai/Quasar-Preview) model
#1407 opened Jun 15, 2026 by SahilChachra Contributor Loading…
fix(server): flush tool call when generation ends in "tool" state (Mistral/Devstral)
#1406 opened Jun 15, 2026 by rinaldofesta Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.