Georgi Gerganov 8406b0924b ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240) ...

* ggml : use blas even if src0 is not F32

* llama : use n_threads_batch only when n_tokens >= 32

ggml-ci

* llama : revert n_threads_batch logic

ggml-ci

2023-11-28 10:32:03 +02:00

615 KiB

Raw Blame History

View Raw