@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
micro_gemm
sgl-kernels
activation.cpp
activation_lut_bf16.cpp
cpu_arch_macros.h
cpu_attn.cpp
cpu_attn_amx.hpp
cpu_attn_amx_fp8.hpp
cpu_attn_fp8.hpp
cpu_attn_impl.hpp
cpu_attn_neon.hpp
cpu_attn_neon_bfmmla.hpp
cpu_attn_rvv.hpp
cpu_attn_vec.hpp
cpu_attn_vec16.hpp
cpu_attn_vsx.hpp
cpu_attn_vxe.hpp
cpu_fused_moe.cpp
cpu_fused_moe_activations.hpp
cpu_fused_moe_int8.cpp
cpu_isa.cpp
cpu_tanhf_neon.hpp
cpu_types.hpp
cpu_types_arm.hpp
cpu_types_riscv.hpp
cpu_types_riscv_defs.hpp
cpu_types_riscv_impl.hpp
cpu_types_scalar.hpp
cpu_types_vsx.hpp
cpu_types_vxe.hpp
cpu_types_x86.hpp
cpu_wna16.cpp
dnnl_helper.cpp
dnnl_helper.h
dnnl_kernels.cpp
float_convert.hpp
generate_cpu_attn_dispatch.py
layernorm.cpp
mamba_cpu.cpp
mamba_kernels.hpp
mla_decode.cpp
pos_encoding.cpp
sampling_kernels.cpp
shm.cpp
spec_decode_utils.cpp
torch_bindings.cpp
utils.cpp
utils.hpp