vllm/csrc/cpu/micro_gemm at main - vllm - Gitea: Git with a cup of tea

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-07 06:18:06 +00:00

Files

T

History

0a6446005d [CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133 )

Signed-off-by: jiang1.li <[email protected]>
Signed-off-by: Fadi Arafeh <[email protected]>
Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
Co-authored-by: Fadi Arafeh <[email protected]>

2026-08-03 14:55:04 +08:00

cpu_micro_gemm_amx.hpp

[CPU][Perf] Accelerate unquantized MoE for AArch64 (#46353 )

2026-06-24 14:14:35 +00:00

cpu_micro_gemm_impl.hpp

[CPU][Perf] INT8 Fused MoE Kernel for Arm CPUs (#48637 )

2026-07-27 05:53:09 +00:00

cpu_micro_gemm_int8_neon.hpp

[CPU][Perf] INT8 Fused MoE Kernel for Arm CPUs (#48637 )

2026-07-27 05:53:09 +00:00

cpu_micro_gemm_neon.hpp

[CPU][Perf] INT8 Fused MoE Kernel for Arm CPUs (#48637 )

2026-07-27 05:53:09 +00:00

cpu_micro_gemm_rvv.hpp

[CPU][RISC-V] Add RVV micro GEMM for WNA16 (#44324 )

2026-06-22 12:53:54 +00:00

cpu_micro_gemm_vec.hpp

[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133 )

2026-08-03 14:55:04 +08:00