Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-05 12:31:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update ggml/src/ggml-cpu/iqp.h

Browse Source 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Bartowski
2026-08-30 08:46:09 -04:00
committed by GitHub
parent 31868838dc
commit 6cdbdf56db
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/iqp.h
+1 -1
View File
@@ -17,7 +17,7 @@ bool ggml_cpu_iqp_mul_mat_id_min_batch(int64_t cne1);
bool ggml_cpu_iqp_supports_mul_mat(const struct ggml_tensor * dst);
// node level test only - per expert eligibility is decided with ggml_cpu_iqp_expert_eligible
// node level test only - per expert eligibility is decided with ggml_cpu_iqp_mul_mat_id_min_batch
bool ggml_cpu_iqp_supports_mul_mat_id(const struct ggml_tensor * dst);
// per thread panel scratch bytes, padded