Merge branch 'v0.0.6_develop_sugon' into 'main'

v0.0.6 See merge request dcutoolkit/deeplearing/autoawq_kernels!1

Merge branch 'v0.0.6_develop_sugon' into 'main'
v0.0.6 See merge request dcutoolkit/deeplearing/autoawq_kernels!1
9f217825 · gaoqiong · b2c05ad6 · 1c46b800 · 9f217825 · 9f217825
Commit 9f217825 authored Jul 03, 2024 by gaoqiong
15 changed files
--- a/awq_ext/quantization/gemv_cuda.h
+++ b/awq_ext/quantization/gemv_cuda.h
--- a/awq_ext/quantization_new/dequantize.cuh
+++ b/awq_ext/quantization_new/dequantize.cuh
--- a/awq_ext/quantization_new/gemm/gemm_cuda.cu
+++ b/awq_ext/quantization_new/gemm/gemm_cuda.cu
--- a/awq_ext/quantization_new/gemm/gemm_cuda.h
+++ b/awq_ext/quantization_new/gemm/gemm_cuda.h
--- a/awq_ext/quantization_new/gemm/semaphore.h
+++ b/awq_ext/quantization_new/gemm/semaphore.h
--- a/awq_ext/quantization_new/gemv/gemv_cuda.cu
+++ b/awq_ext/quantization_new/gemv/gemv_cuda.cu
--- a/awq_ext/quantization_new/gemv/gemv_cuda.h
+++ b/awq_ext/quantization_new/gemv/gemv_cuda.h
--- a/awq_ext/vllm/activation.cu
+++ b/awq_ext/vllm/activation.cu
--- a/awq_ext/vllm/activation.h
+++ b/awq_ext/vllm/activation.h
--- a/awq_ext/vllm/moe_alig_block.cu
+++ b/awq_ext/vllm/moe_alig_block.cu
--- a/awq_ext/vllm/moe_alig_block.h
+++ b/awq_ext/vllm/moe_alig_block.h
--- a/awq_ext/vllm/topk_softmax_kernels.cu
+++ b/awq_ext/vllm/topk_softmax_kernels.cu
--- a/awq_ext/vllm/topk_softmax_kernels.h
+++ b/awq_ext/vllm/topk_softmax_kernels.h
--- a/scripts/download_wheels.sh
+++ b/scripts/download_wheels.sh
--- a/setup.py
+++ b/setup.py