[kernel] Fused embedding kernel (#53677)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
This commit is contained in:
@@ -430,6 +430,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
|
||||
"csrc/libtorch_stable/cuda_utils_kernels.cu"
|
||||
"csrc/libtorch_stable/activation_kernels.cu"
|
||||
"csrc/libtorch_stable/ngram_embedding_kernels.cu"
|
||||
"csrc/libtorch_stable/vocab_parallel_embedding_kernels.cu"
|
||||
"csrc/libtorch_stable/quantization/activation_kernels.cu"
|
||||
"csrc/libtorch_stable/quantization/w8a8/int8/scaled_quant.cu"
|
||||
"csrc/libtorch_stable/quantization/w8a8/fp8/common.cu"
|
||||
|
||||
Reference in New Issue
Block a user