ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 15:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Change flash attention to be on by default

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-10-25 09:32:01 +03:00
parent 9dc0c89bc9
commit 6d05977940
4 changed files with 18 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
common/common.cpp
View File

@@ -994,8 +994,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.cont_batching = false;
return true;
}
if (arg == "-fa" || arg == "--flash-attn") {
params.flash_attn = true;
if (arg == "-no-fa" || arg == "--no-flash-attn") {
params.flash_attn = false;
return true;
}
if (arg == "-mla" || arg == "--mla-use") {
@@ -1804,7 +1804,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", "-ub, --ubatch-size N", "physical maximum batch size (default: %d)", params.n_ubatch });
options.push_back({ "*", " --keep N", "number of tokens to keep from the initial prompt (default: %d, -1 = all)", params.n_keep });
options.push_back({ "*", " --chunks N", "max number of chunks to process (default: %d, -1 = all)", params.n_chunks });
options.push_back({ "*", "-fa, --flash-attn", "enable Flash Attention (default: %s)", params.flash_attn ? "enabled" : "disabled" });
options.push_back({ "*", "-no-fa, --no-flash-attn", "disable Flash Attention (default: %s)", params.flash_attn ? "enabled" : "disabled" });
options.push_back({ "*", "-mla, --mla-use", "enable MLA (default: %d)", params.mla_attn });
options.push_back({ "*", "-amb, --attention-max-batch", "max batch size for attention computations (default: %d)", params.attn_max_batch});
options.push_back({ "*", "-no-fmoe, --no-fused-moe", "disable fused MoE (default: %s)", params.fused_moe_up_gate ? "enabled" : "disabled" });