mirror of
https://github.com/ollama/ollama.git
synced 2026-09-21 13:38:14 -05:00
Includes quantized matmul corruption fix, which impacts nvfp4 multimodal models (gemma4 vision towers). Deferring wiring up the new MLX-C thread-local stream/sync APIs for now.
1 line
40 B
Plaintext
1 line
40 B
Plaintext
d9add9d11f3154111a4c85f267ec2fd307ecd18e |