A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 09:15 UTC
cache_kernel -> cache_kernels
Woosuk Kwon committed
Feb 16, 2023 at 20:05 UTC
ffad4e1e031a9facda4cab5b9fff31b47157aebc
2 files changed
+1
-1
csrc/cache_kernels.cu
renamed
setup.py
+1
-1
@@ -10,7 +10,7 @@ ext_modules = []
10
# Cache operations.
11
cache_extension = cpp_extension.CUDAExtension(
12
name='cacheflow.ops',
13
- sources=['csrc/cache.cpp', 'csrc/cache_kernel.cu'],
13
+ sources=['csrc/cache.cpp', 'csrc/cache_kernels.cu'],
14
extra_compile_args={'cxx': CXX_FLAGS, 'nvcc': NVCC_FLAGS},
15
)
16
ext_modules.append(cache_extension)