CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama: -fa 1/0/-1 aliases for -fa on/off/auto (#15746)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-09-02 18:17:26 +02:00
committed by GitHub
parent 0a2a3841e8
commit c466abe158
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
common/arg.cpp
View File

@@ -1548,11 +1548,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"-fa", "--flash-attn"}, "FA", {"-fa", "--flash-attn"}, "FA",
string_format("set Flash Attention use ('on', 'off', or 'auto', default: '%s')", llama_flash_attn_type_name(params.flash_attn_type)), string_format("set Flash Attention use ('on', 'off', or 'auto', default: '%s')", llama_flash_attn_type_name(params.flash_attn_type)),
[](common_params & params, const std::string & value) { [](common_params & params, const std::string & value) {
if (value == "on" || value == "enabled") { if (value == "on" || value == "enabled" || value == "1") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED; params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED;
} else if (value == "off" || value == "disabled") { } else if (value == "off" || value == "disabled" || value == "0") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_DISABLED; params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_DISABLED;
} else if (value == "auto") { } else if (value == "auto" || value == "-1") {
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_AUTO; params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_AUTO;
} else { } else {
throw std::runtime_error(string_format("error: unkown value for --flash-attn: '%s'\n", value.c_str())); throw std::runtime_error(string_format("error: unkown value for --flash-attn: '%s'\n", value.c_str()));