Skip to content

Pull requests: ml-explore/mlx-lm

New pull request New
32 Open 384 Closed
32 Open 384 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

Make MambaCache compatible with batch generation for nemotron-h
#690 opened Dec 18, 2025 by nikhilmitrax Loading…
5
Add tokenizer_config support to LoRA YAML configuration
#688 opened Dec 17, 2025 by breitburg Loading…
Add server logging and stop generation on client disconnect
#677 opened Dec 15, 2025 by otarkhan Loading…
Add MiniMax M2 tool call parser support
#665 opened Dec 8, 2025 by otarkhan Loading…
4 tasks done
Add logits_processors support to batch_generate
#635 opened Nov 28, 2025 by lazarust Loading…
1
Add online test (user side observation)
#604 opened Nov 11, 2025 by yiakwy-xpu-ml-framework-team Loading…
1
Add Ouro
#599 opened Nov 9, 2025 by kernelpool Loading…
2
Fix tool calling with openai server
#598 opened Nov 8, 2025 by code-ghalib Loading…
Added optional accuracy reporting while training and evaluating models
#595 opened Nov 7, 2025 by jyork03 Loading…
Fix : mlx-server for chunked request (to support one-api, curl)
#589 opened Nov 3, 2025 by yiakwy-xpu-ml-framework-team Loading…
24
Addding Emu3
#585 opened Nov 2, 2025 by Goekdeniz-Guelmez • Draft
Normalize scheduler/warmup step-like arguments by grad_accumulation_steps; warmup-only configuration, sane argument defaults and tests
#582 opened Nov 1, 2025 by jyork03 Loading…
Add RWKV7
#580 opened Oct 31, 2025 by MollySophia Loading…
Add LLada2 MoE
#560 opened Oct 18, 2025 by kernelpool Loading…
1
Feature Enhancement: Auto-detect & resume iteration from checkpoint files
#556 opened Oct 16, 2025 by dotvignesh Loading…
Add epoch argument in trainer
#523 opened Oct 2, 2025 by Goekdeniz-Guelmez Loading…
5
Implement dpo tuning
#417 opened Aug 31, 2025 by eghuzefa Loading…
3
Native support for tekken/mistral
#363 opened Aug 9, 2025 by graelo Loading…
3
Add early stopping
#331 opened Jul 26, 2025 by hansvdam Loading…
2
Improve /v1/models/:id endpoint
#315 opened Jul 16, 2025 by mohd-akram Loading…
3
adding Support for Dream Architecture
#270 opened Jul 3, 2025 by Goekdeniz-Guelmez • Draft
12
More dynamic quant
#240 opened Jun 17, 2025 by angeloskath • Draft
3
Identifying layers to convert to LoRA by pattern or indicating all linear layers
#228 opened Jun 11, 2025 by chimezie Loading…
6
generate: Support stop_words
#194 opened May 26, 2025 by madroidmaq Loading…
3
Performance regression when reusing trainer with gradient checkpointing
#167 opened May 11, 2025 by cblomert Loading…
2
ProTip! What’s not been updated in a month: updated:<2025-11-25.