ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Option to use MLA without a transposed cache

Browse Source 
The `-mla` command line option turns into an int from a bool.
mla = 0: use standard attention
mla = 1: use MLA with transposed cache
mla > 1: use MLA without transposed cache
This commit is contained in:
Iwan Kawrakow
2025-02-27 10:28:54 +02:00
parent 51029edfdf
commit 407ca33b2a
6 changed files with 64 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
common/common.cpp
View File

@@ -851,7 +851,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
if (arg == "-mla" || arg == "--mla-use") {
params.mla_attn = true;
CHECK_ARG
params.mla_attn = std::stoi(argv[i]);
return true;
}
if (arg == "-fmoe" || arg == "--fused-moe") {
@@ -1514,7 +1515,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
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({ "*", "-mla, --mla-use", "enable MLA (default: %s)", params.mla_attn ? "enabled" : "disabled" });
options.push_back({ "*", "-mla, --mla-use", "enable MLA (default: %d)", params.mla_attn });
options.push_back({ "*", "-fmoe, --fused-moe", "enable fused MoE (default: %s)", params.fused_moe_up_gate ? "enabled" : "disabled" });
options.push_back({ "*", "-p, --prompt PROMPT", "prompt to start generation with\n"
"in conversation mode, this will be used as system prompt\n"
@@ -3357,7 +3358,7 @@ void yaml_dump_non_result_info(FILE * stream, const gpt_params & params, const l
fprintf(stream, "simple_io: %s # default: false\n", params.simple_io ? "true" : "false");
fprintf(stream, "cont_batching: %s # default: false\n", params.cont_batching ? "true" : "false");
fprintf(stream, "flash_attn: %s # default: false\n", params.flash_attn ? "true" : "false");
fprintf(stream, "mla_attn: %s # default: false\n", params.mla_attn ? "true" : "false");
fprintf(stream, "mla_attn: %d # default: 0\n", params.mla_attn);
fprintf(stream, "fused_moe: %s # default: false\n", params.fused_moe_up_gate ? "true" : "false");
fprintf(stream, "temp: %f # default: 0.8\n", sparams.temp);