[Core] Support loading GGUF model (#5191)
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
@@ -242,6 +242,11 @@ echo 'vLLM isort: Done'
|
||||
# NOTE: Keep up to date with .github/workflows/clang-format.yml
|
||||
CLANG_FORMAT_EXCLUDES=(
|
||||
'csrc/moe/topk_softmax_kernels.cu'
|
||||
'csrc/quantization/gguf/ggml-common.h'
|
||||
'csrc/quantization/gguf/dequantize.cuh'
|
||||
'csrc/quantization/gguf/vecdotq.cuh'
|
||||
'csrc/quantization/gguf/mmq.cuh'
|
||||
'csrc/quantization/gguf/mmvq.cuh'
|
||||
)
|
||||
|
||||
# Format specified files with clang-format
|
||||
|
||||
Reference in New Issue
Block a user