ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-17 14:28:07 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

CUDA: MMQ support for iq4_nl, iq4_xs (llama/8278)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-07-05 09:06:31 +02:00
committed by Georgi Gerganov
parent 73703a144f
commit 5dc636a65a
7 changed files with 226 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/template-instances/generate_cu_files.py
View File

@ -22,7 +22,8 @@ SOURCE_FATTN_WMMA_CASE = "DECL_FATTN_WMMA_F16_CASE({head_size}, {cols_per_block}
TYPES_MMQ = [
"GGML_TYPE_Q4_0", "GGML_TYPE_Q4_1", "GGML_TYPE_Q5_0", "GGML_TYPE_Q5_1", "GGML_TYPE_Q8_0",
"GGML_TYPE_Q2_K", "GGML_TYPE_Q3_K", "GGML_TYPE_Q4_K", "GGML_TYPE_Q5_K", "GGML_TYPE_Q6_K"
"GGML_TYPE_Q2_K", "GGML_TYPE_Q3_K", "GGML_TYPE_Q4_K", "GGML_TYPE_Q5_K", "GGML_TYPE_Q6_K",
"GGML_TYPE_IQ4_NL", "GGML_TYPE_IQ4_XS"
]
SOURCE_MMQ = """// This file has been autogenerated by generate_cu_files.py, do not edit manually.

5
ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu Normal file
View File

@ -0,0 +1,5 @@
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../mmq.cuh"
DECL_MMQ_CASE(GGML_TYPE_IQ4_NL);

5
ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu Normal file
View File

@ -0,0 +1,5 @@
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
#include "../mmq.cuh"
DECL_MMQ_CASE(GGML_TYPE_IQ4_XS);