This website requires JavaScript.
Explore
Help
Register
Sign In
EngineX-Mthreads
/
enginex-mthreads-vllm
Watch
4
Star
0
Fork
0
You've already forked enginex-mthreads-vllm
Code
Issues
Pull Requests
Actions
Projects
Releases
Wiki
Activity
Files
v0.13
enginex-mthreads-vllm
/
csrc
/
quantization
/
fp4
History
xiezhongtao
2bd9bd4cc2
refactor: 统一硬件相关头文件引用
...
将分散在各文件中的CUDA/HIP/MUSA硬件相关头文件引用统一到vendors目录下的对应头文件中,提高代码可维护性。移除重复的头文件引用,优化构建配置。
2026-01-20 10:14:31 +08:00
..
activation_nvfp4_quant_fusion_kernels.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_blockwise_moe_kernel.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_experts_quant.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_quant_entry.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_quant_kernels.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_scaled_mm_entry.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_scaled_mm_kernels.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_scaled_mm_sm120_kernels.cu
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00
nvfp4_utils.cuh
refactor: 统一硬件相关头文件引用
2026-01-20 10:14:31 +08:00