tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Force FP32 compute in GLM4 FFN Down (#13101)

Browse Source 
* Force FP32 compute in cuBLAS GEMM

* Revert "Force FP32 compute in cuBLAS GEMM"

This reverts commit 6efd872732.

* Force F32 compute in GLM4 ffn down

* Edit comment to clarify issue

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
City
2025-04-25 14:38:34 +02:00
committed by GitHub
parent edb18b6e8f
commit 558a764713
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-graph.cpp
View File

@ -803,6 +803,10 @@ ggml_tensor * llm_graph_context::build_ffn(
if (down) {
cur = build_lora_mm(down, cur);
if (arch == LLM_ARCH_GLM4) {
// GLM4 seems to have numerical issues with half-precision accumulators
ggml_mul_mat_set_prec(cur, GGML_PREC_F32);
}
}
if (down_b) {