DeepseekMoE support with Fused MoE kernel (#2453)

Co-authored-by: roy <jasonailu87@gmail.com>
2024-01-30 13:19:48 +08:00
parent ea8489fce2
commit 5d60def02c
9 changed files with 924 additions and 0 deletions
--- a/setup.py
+++ b/setup.py
@@ -309,6 +309,7 @@ vllm_extension_sources = [
    "csrc/quantization/squeezellm/quant_cuda_kernel.cu",
    "csrc/quantization/gptq/q_gemm.cu",
    "csrc/cuda_utils_kernels.cu",
+    "csrc/moe_align_block_size_kernels.cu",
    "csrc/pybind.cpp",
 ]