Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : adjust logic for offloading ops to weight's backend (#25832)

Browse Source 
* ggml : adjust logic for offloading ops to weight's backend

* llama : dsv4 graph fixes
This commit is contained in:
Georgi Gerganov
2026-07-27 14:54:46 +03:00
committed by GitHub
parent 7ef790f90a
commit dee2a846b8
3 changed files with 34 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/deepseek4.cpp
+5 -1
View File
@@ -1133,6 +1133,10 @@ llama_model_deepseek4::graph::graph(const llama_model & model, const llm_graph_p
&post, &comb, il);
cb(cur, "hc_ffn_pre", il);
ggml_build_forward_expand(gf, residual);
ggml_build_forward_expand(gf, post);
ggml_build_forward_expand(gf, comb);
cur = build_norm(cur, model.layers[il].ffn_norm, nullptr, LLM_NORM_RMS, il);
cb(cur, "ffn_norm", il);
@@ -1175,7 +1179,7 @@ llama_model_deepseek4::graph::graph(const llama_model & model, const llm_graph_p
inpL = build_hc_post(cur, residual, post, comb, il);
inpL = build_cvec(inpL, il);
cb(inpL, "l_out", il);
cb(inpL, "l_last", il);
}
if (inp_out_ids) {