vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

imatrix : offload to GPU support

Browse source
This commit is contained in:
Georgi Gerganov 2024-01-15 16:18:11 +02:00
parent e0493800ce
commit 0b2fca9a9f
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 48 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml.h
View file

@ -2075,12 +2075,6 @@ extern "C" {
GGML_API void ggml_init_iq2_quantization(enum ggml_type type);
GGML_API void ggml_deinit_iq2_quantization(enum ggml_type type);
//
// Importance matrix
//
typedef void(*ggml_collect_imatrix_t)(const struct ggml_tensor * src0, const struct ggml_tensor * src1);
GGML_API void ggml_set_imatrix_collection(ggml_collect_imatrix_t imatrix_collect);
//
// gguf
//