Rehan KhanandBob fd0216d3b5 [Bugfix][CPU] Fix fused Gumbel-max wrapping-window bias (#60221) ...

Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Bob <bob@ibm.com>

2026-10-08 15:15:53 +08:00

..

micro_gemm

[HARDWARE][POWER] Enable W8A8 INT8 MoE on POWER (#55316)

2026-09-17 21:45:13 +08:00

sgl-kernels

[Bugfix][CPU] Fix macOS build on Apple Clang < 17: structured binding… (#58932)

2026-10-02 10:01:07 +08:00

activation_lut_bf16.cpp

…

activation.cpp

…

cpu_arch_macros.h

…

cpu_attn_amx_fp8.hpp

…

cpu_attn_amx.hpp

…

cpu_attn_fp8.hpp

…

cpu_attn_impl.hpp

[Bugfix][DiffusionGemma] Read the causal mask as int32 and compile the sample step (#59992)

2026-10-06 19:25:51 +08:00

cpu_attn_neon_bfmmla.hpp

[CPU][Perf] refactor paged attention for Arm CPUs (#56045)

2026-09-20 12:25:13 +08:00

cpu_attn_neon.hpp

[CPU][Perf] refactor paged attention for Arm CPUs (#56045)

2026-09-20 12:25:13 +08:00

cpu_attn_rvv.hpp

…

cpu_attn_vec16.hpp

…

cpu_attn_vec.hpp

…

cpu_attn_vsx.hpp

…

cpu_attn_vxe.hpp

…

cpu_attn.cpp

[Bugfix][DiffusionGemma] Read the causal mask as int32 and compile the sample step (#59992)

2026-10-06 19:25:51 +08:00

cpu_fused_moe_activations.hpp

…

cpu_fused_moe_int8.cpp

[HARDWARE][POWER] Enable W8A8 INT8 MoE on POWER (#55316)

2026-09-17 21:45:13 +08:00

cpu_fused_moe.cpp

…

cpu_isa.cpp

[CPU] Add CPU FP8 W8A8 linear/MoE support (#49942)

2026-09-18 17:59:42 +08:00

cpu_tanhf_neon.hpp

…

cpu_types_arm.hpp

…

cpu_types_riscv_defs.hpp

…

cpu_types_riscv_impl.hpp

…

cpu_types_riscv.hpp

…

cpu_types_scalar.hpp

…

cpu_types_vsx.hpp

[Hardware][Power] Enable W4A16 (AWQ & GPTQ) quantization on POWER10 using VSX (#59149)

2026-09-30 19:44:48 +08:00

cpu_types_vxe.hpp

…

cpu_types_x86.hpp

…

cpu_types.hpp

…

cpu_wna16.cpp

[Hardware][Power] Enable W4A16 (AWQ & GPTQ) quantization on POWER10 using VSX (#59149)

2026-09-30 19:44:48 +08:00

dnnl_helper.cpp

…

dnnl_helper.h

…

dnnl_kernels.cpp

…

float_convert.hpp

…

generate_cpu_attn_dispatch.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

layernorm.cpp

…

mamba_cpu.cpp

…

mamba_kernels.hpp

…

mla_decode.cpp

…

pos_encoding.cpp

…

sampling_kernels.cpp

[Bugfix][CPU] Fix fused Gumbel-max wrapping-window bias (#60221)

2026-10-08 15:15:53 +08:00

shm.cpp

…

spec_decode_utils.cpp

…

torch_bindings.cpp

[CPU] Conv1d optimised kernel for aarch64 (#54093)

2026-09-30 20:23:42 +08:00

utils.cpp

…

utils.hpp

…