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

Remove Q4_3 which is no better than Q5 (#1218)

Browse source
This commit is contained in:
Stephan Walter 2023-04-28 23:10:43 +00:00 • committed by GitHub
parent 7f15c5c477
commit 36d19a603b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 21 additions and 359 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml-cuda.h
View file

@ -34,7 +34,6 @@ void ggml_cuda_pool_free(void * ptr, size_t size);
void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q5_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q5_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);