LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

Add extra nodes when dealing with MLA and amb (#1899)

Browse Source
This commit is contained in:
Kawrakow
2026-05-29 15:17:24 +03:00
committed by GitHub
parent e75337fec3
commit 8960c5ba5e
60 changed files with 112 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+4
View File
@@ -1788,6 +1788,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
if (arg == "-amb" || arg == "--attention-max-batch") {
CHECK_ARG
params.attn_max_batch = std::stoi(argv[i]);
if (params.attn_max_batch > 0 && params.attn_max_batch < 128) {
LLAMA_LOG_WARN("XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX amb = %d is too low. Changing to 128\n", params.attn_max_batch);
params.attn_max_batch = 128;
}
return true;
}
if (arg == "-no-fmoe" || arg == "--no-fused-moe") {