Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '649495c9d915a284aeec5bca5d0efaa6d1bc7c87' into concedo_experimental

Browse Source 
# Conflicts:
#	CONTRIBUTING.md
#	SECURITY.md
#	docs/backend/SYCL.md
#	examples/sycl/run-llama2.sh
#	examples/sycl/run-llama3.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-run-llama3.bat
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-backend-ops.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo
2025-12-03 18:43:46 +08:00
parent 7316c24bf6 649495c9d9
commit 83269df91b
29 changed files with 4593 additions and 3728 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-graph.cpp
-6
View File
@@ -810,9 +810,6 @@ ggml_tensor * llm_graph_context::build_ffn(
GGML_ABORT("fatal error");
}
//expand here so that we can fuse ffn gate
ggml_build_forward_expand(gf, cur);
if (gate && type_gate == LLM_FFN_PAR) {
cur = ggml_mul(ctx0, cur, tmp);
cb(cur, "ffn_gate_par", il);
@@ -1093,9 +1090,6 @@ ggml_tensor * llm_graph_context::build_moe_ffn(
GGML_ABORT("fatal error");
}
//expand here so that we can fuse ffn gate
ggml_build_forward_expand(gf, cur);
experts = build_lora_mm_id(down_exps, cur, selected_experts); // [n_embd, n_expert_used, n_tokens]
cb(experts, "ffn_moe_down", il);