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

ggml : reuse quantum structs across backends (#5943)

Browse source 
* ggml : reuse quant blocks across backends

ggml-ci

* ggml : define helper constants only for CUDA and SYCL

ggml-ci

* ggml : define helper quantum constants for SYCL

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-03-12 14:27:20 +02:00 • committed by GitHub
parent 184215e783
commit 8030da7afe
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 470 additions and 881 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-metal.m
View file

@ -336,7 +336,7 @@ static struct ggml_metal_context * ggml_metal_init(int n_cb) {
NSMutableDictionary * prep = [NSMutableDictionary dictionary];
#ifdef GGML_QKK_64
prep[@"QK_K"] = @(64);
prep[@"GGML_QKK_64"] = @(1);
#endif
MTLCompileOptions* options = [MTLCompileOptions new];