ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-10 00:10:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use standard output calculation for MiniMax-M2 graph parallel (#1199)

Browse Source
This commit is contained in:
Kawrakow
2026-01-29 09:06:40 +02:00
committed by GitHub
parent f0c61adacc
commit 686fd1ebec
1 changed files with 1 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/llama-build-context.cpp
View File

@@ -8833,17 +8833,7 @@ ggml_cgraph* llm_build_context::build_minimaxm2() {
inpL = cur;
}
cur = inpL;
cur = llm_build_norm(ctx0, cur,
hparams, model.output_norm, NULL,
LLM_NORM_RMS, cb, -1);
cb(cur, "result_norm", -1);
// lm_head
cur = llm_build_lora_mm(lctx, ctx0, model.output, cur);
cur = build_output(lctx, ctx0, inpL, model.output, model.output_norm, cb);
cb(cur, "result_output", -1);
ggml_build_forward_expand(gf, cur);