Module ops 

GPU kernel host-side dispatch functions.

Each submodule implements dispatch for a specific kernel family.

Modules

argmax

Greedy argmax GPU dispatch — finds the index of the maximum value in a float array entirely on the GPU.

argsort

GPU-accelerated argsort (descending) for MoE top-K routing.

copy

GPU-accelerated strided copy for making tensors contiguous.

cumsum

Cumulative sum (inclusive prefix sum) along the last axis.

dense_gemm

Dense F16 matrix multiply for the lm_head vocabulary projection.

dense_mm_bf16

Dense bf16 × f32 → f32 matmul using Apple M3+ tensor cores (mpp::tensor_ops::matmul2d).

elementwise

GPU-accelerated elementwise operations: add, multiply, and dtype cast.

embedding

GPU-accelerated quantized embedding table lookup.

encode_helpers

Helper utilities for encoding compute dispatches with inline constant parameters (bytes) alongside buffer bindings.

flash_attn_prefill

Flash-attention-style tiled prefill kernel — host dispatch.

flash_attn_prefill_blk

Flash-attention tile-skip pre-pass — host dispatch.

flash_attn_prefill_d512

Flash-attention-style tiled prefill kernel — NSG=8 D=512 host dispatch.

flash_attn_prefill_mask

SWA / causal attention-mask builder for the flash_attn_prefill kernels.

flash_attn_vec

Flash attention vector kernel dispatch — SIMD-vectorized decode-path SDPA.

flash_attn_vec_tq

Flash attention vector kernel dispatch for TurboQuant-compressed KV cache.

flash_attn_vec_tq_hb

Flash attention vector kernel dispatch for higher-bit TurboQuant KV cache.

fused_head_norm_rope

Fused per-head RMS normalization + NeoX RoPE GPU dispatch (bf16).

fused_norm_add

Fused RMS normalization + residual addition GPU dispatch (bf16).

fused_residual_norm

Fused residual addition + RMS normalization GPU dispatch (bf16).

fwht_standalone

Standalone Fast Walsh-Hadamard Transform dispatch (SIMD shuffle, zero barriers).

gated_delta_net

Gated DeltaNet fused GPU dispatch — the centerpiece of Qwen3.5 linear-attention layers.

gather

GPU-accelerated gather / index_select along dim=0.

gather_bench

Gather throughput microbenchmark dispatch.

gelu

GELU activation (pytorch_tanh variant) GPU dispatch.

hadamard

Fast Walsh-Hadamard Transform (FWHT) GPU kernel dispatch.

hadamard_quantize_kv

Hadamard-quantize KV cache kernel dispatch (ADR-007 Phase 1.1).

kv_cache_copy

KV cache GPU copy dispatch.

l2_norm

L2 Normalization GPU dispatch.

moe_dispatch

GPU-accelerated MoE expert dispatch (Stage 1: loop over selected experts).

moe_gate

GPU-accelerated MoE gating: parallel top-K expert selection with softmax routing.

quantized_matmul

Quantized matrix multiplication host-side dispatch.

quantized_matmul_ggml

GGML block-format quantized matrix-vector multiply dispatch.

quantized_matmul_id

Expert-routed (MoE) quantized matrix-vector multiply dispatch.

quantized_matmul_id_ggml

GGML block-format expert-routed (MoE) quantized matrix-vector multiply dispatch.

rms_norm

RMS Normalization GPU dispatch.

rope

Rotary Position Embedding (RoPE) GPU dispatch.

rope_multi

Multi-section Rotary Position Embedding with optional interleaved mode.

scale_mask_softmax

Fused scale-mask-softmax for non-flash-attention prefill.

sdpa

Scaled dot-product attention (SDPA) host dispatch.

sdpa_sliding

Sliding-window scaled dot-product attention host dispatch.

sigmoid_mul

Elementwise sigmoid-gated multiply: out[i] = x[i] * sigmoid(gate[i]).

softcap

Softcap (tanh-based logit capping) GPU dispatch.

softmax

Numerically stable softmax GPU dispatch.

softmax_sample

Temperature-scaled softmax + categorical sample, entirely on GPU.

ssm_conv

SSM depthwise causal 1D conv + SiLU GPU dispatch.

top_k

GPU top-K dispatch — returns the K largest elements of a float array.

tq_dequantize_kv

TQ KV dequantize kernel dispatch — iter-20 Leg F ablation.

transpose

GPU-accelerated 2D matrix transpose.

tri_solve

Lower-triangular unit-diagonal solve: X = L \ B.