mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-31 08:51:55 +00:00
The fused operation was grabbing the epsilon value from the wrong place. Add an env var to disable fusion. Add some missing checks for supported shapes/types. Handle fused rms_norm+mul in check_results.
211 KiB
211 KiB