diff options
Diffstat (limited to 'src/llama.cpp')
| -rw-r--r-- | src/llama.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/llama.cpp b/src/llama.cpp index 94a939d8..dca03ade 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -16816,7 +16816,7 @@ struct llama_context * llama_new_context_with_model( params.flash_attn = false; } - if (params.type_v != GGML_TYPE_F16 && !params.flash_attn) { + 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__); return nullptr; } |