mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-24 07:28:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama/parsers/renderers: nemotron 3 nano (#13489)

Browse Source 
---------

Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
This commit is contained in:
Parth Sareen
2025-12-15 18:00:08 -08:00
committed by GitHub
parent 7b95087b9d
commit 7e3ea813c1
13 changed files with 2364 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
llama/llama.cpp/src/llama-graph.cpp vendored
View File

@@ -1089,6 +1089,16 @@ ggml_tensor * llm_graph_context::build_moe_ffn(
cur = ggml_relu(ctx0, cur);
cb(cur, "ffn_moe_relu", il);
} break;
case LLM_FFN_RELU_SQR:
if (gate_exps) {
// TODO: add support for gated squared relu
GGML_ABORT("fatal error: gated squared relu not implemented");
} else {
cur = ggml_relu(ctx0, cur);
cur = ggml_sqr(ctx0, cur);
cb(cur, "ffn_moe_relu_sqr", il);
}
break;
default:
GGML_ABORT("fatal error");
}