diff options
Diffstat (limited to 'src/llama.cpp')
| -rw-r--r-- | src/llama.cpp | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/src/llama.cpp b/src/llama.cpp index b2553802..0817c53c 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -17768,10 +17768,10 @@ struct llama_context * llama_new_context_with_model( params.flash_attn = false; } - if (params.flash_attn && model->hparams.n_embd_head_k != model->hparams.n_embd_head_v) { - LLAMA_LOG_WARN("%s: flash_attn requires n_embd_head_k == n_embd_head_v - forcing off\n", __func__); - params.flash_attn = false; - } + //if (params.flash_attn && model->hparams.n_embd_head_k != model->hparams.n_embd_head_v) { + // LLAMA_LOG_WARN("%s: flash_attn requires n_embd_head_k == n_embd_head_v - forcing off\n", __func__); + // params.flash_attn = false; + //} if (params.type_v != GGML_TYPE_F16 && params.type_v != GGML_TYPE_BF16 && !params.flash_attn) { LLAMA_LOG_ERROR("%s: V cache quantization requires flash_attn\n", __func__); |