Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

ci: Fix windows build (#14754)
Daniel Hiltgen committed 8 months ago
62d1f01
10e51c5
3e06bde
rocm: update linux to v7.2 (#14391)
Daniel Hiltgen committed 8 months ago
ebb1b9e
afb4c62
mlx: int4 groupsize 64 (#14682)
Patrick Devine committed 8 months ago
e790dc4
build: smarter docker parallelism (#14653)
Daniel Hiltgen committed 8 months ago
288077c
create: fix localhost handling (#14681)
Daniel Hiltgen committed 8 months ago
4425c54
docs: format compat docs (#14678)
Michael Yang committed 8 months ago
778899a
1af850e
9b0c7cc
mlx: prevent remote creation mismatch (#14651)
Daniel Hiltgen committed 8 months ago
6928630
cmd: use native Ollama API endpoint for OpenClaw (#14649)
Bruce MacDonald committed 8 months ago
15732f0
cmd: add qwen3.5 context length for launch (#14626)
Parth Sareen committed 8 months ago
562c76d
server: loosen thinking level constraint (#14625)
Parth Sareen committed 8 months ago
122c68c
model: fix renderer and parser for qwen3.5 (#14605)
Jeffrey Morgan committed 8 months ago
82848a7
e9f6ea2
chore: remove old imagegen LLMs models (#14597)
Patrick Devine committed 8 months ago
110eff0
Reapply "don't require pulling stubs for cloud models"
Jeffrey Morgan committed 8 months ago
799e51d
don't require pulling stubs for cloud models (#14574)
Devon Rifkin committed 8 months ago
8207e55
mlx: Remove peak memory from the API
Jesse Gross committed 8 months ago
ad16bff
mlxrunner: Refcount pinned tensors
Jesse Gross committed 8 months ago
c1e3ef4