Skip to content

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

Commits on main

server: verify digest is not empty on create (#14555)
Bruce MacDonald committed 8 months ago
23d4cad
8da09b1
mlxrunner: Fix prompt eval timing and count metrics
Jesse Gross committed 8 months ago
a60b9ad
mlxrunner: Enforce model context limit
Jesse Gross committed 8 months ago
a16f966
mlxrunner: Report actual memory usage from runner
Jesse Gross committed 8 months ago
638faea
mlxrunner: Fix panic on full KV cache hit
Jesse Gross committed 8 months ago
dd5eb63
show peak memory usage (#14485)
Patrick Devine committed 8 months ago
79917cf
model: fix qwen3 tool calling in thinking (#14477)
Jeffrey Morgan committed 8 months ago
d98dda4
4e57d20
model: add support for qwen3.5-27b model (#14415)
Jeffrey Morgan committed 8 months ago
7f9efd5
model: support for qwen3.5 architecture (#14378)
Jeffrey Morgan committed 8 months ago
da70c32
ggml: ensure tensor size is valid (#14406)
Bruce MacDonald committed 8 months ago
9d902d6
update mlx-c bindings to 0.5.0 (#14380)
Daniel Hiltgen committed 9 months ago
f4f0a4a
model: improvements to LFM architectures (#14368)
Jeffrey Morgan committed 9 months ago
4b2ac1f
8daf47f
5c73c4e
models: add nemotronh architecture support (#14356)
Jeffrey Morgan committed 9 months ago
0ade920