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

cann: support q4_0 model (#8822)

Browse source
This commit is contained in:
wangshuai09 2024-08-05 12:22:30 +08:00 • committed by GitHub
parent 0d6fb52be0
commit c02b0a8a4d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 357 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml/src/ggml-cann/kernels/CMakeLists.txt
View file

@ -9,6 +9,7 @@ file(GLOB SRC_FILES
get_row_q8_0.cpp
quantize_f32_q8_0.cpp
quantize_f16_q8_0.cpp
quantize_float_to_q4_0.cpp
dup.cpp
)
@ -29,4 +30,4 @@ ascendc_library(ascendc_kernels STATIC
${SRC_FILES}
)
#ascendc_compile_definitions(ascendc_kernels PRIVATE -DASCENDC_DUMP)
# ascendc_compile_definitions(ascendc_kernels PRIVATE -DASCENDC_DUMP)