[Kernel][Quantization] Integrate block-quantized CUTLASS kernels for DeepSeekV3 (#12587)
Integrates the block-quantized kernels introduced in https://github.com/vllm-project/vllm/pull/11868 for use in linear layers. Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
@@ -324,6 +324,13 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
ops.def("cutlass_scaled_mm_supports_fp8(int cuda_device_capability) -> bool");
|
||||
ops.impl("cutlass_scaled_mm_supports_fp8", &cutlass_scaled_mm_supports_fp8);
|
||||
|
||||
// Check if cutlass scaled_mm supports block quantization (used by DeepSeekV3)
|
||||
ops.def(
|
||||
"cutlass_scaled_mm_supports_block_fp8(int cuda_device_capability) -> "
|
||||
"bool");
|
||||
ops.impl("cutlass_scaled_mm_supports_block_fp8",
|
||||
&cutlass_scaled_mm_supports_fp8);
|
||||
|
||||
// Check if cutlass sparse scaled_mm is supported for CUDA devices of the
|
||||
// given capability
|
||||
ops.def(
|
||||
|
||||
Reference in New Issue
Block a user