mirror of
https://github.com/ollama/ollama.git
synced 2026-10-20 18:41:17 +00:00
4ea3472496
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
No EOL
40 B
Text
1 line
No EOL
40 B
Text
ebc88f10caa1b625e6b581437a8dea6df8a70085 |