ggml-org/llama.cpp b9510

on GitHub

ggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD128 (#22209)

• ggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD128

Optimize the inner loop of ggml_vec_dot_q4_1_q8_1_generic using
WASM SIMD128 intrinsics, gated behind #ifdef wasm_simd128 so
non-wasm builds are completely unaffected.

Approach:

• single wasm_v128_load covers all 32 packed 4-bit weights
• nibbles unpacked via AND/SHR into two u8x16 registers
• widened to i16 before multiply (WASM SIMD has no i8*i8 instruction)
• 4x wasm_i32x4_dot_i16x8 calls accumulate all 32 element pairs
• horizontal reduce via 4x wasm_i32x4_extract_lane

Benchmark (node v25, emcc -O3 -msimd128, 64 blocks x QK8_1=32,
200k iterations):

Correctness verified against scalar reference across 10 random seeds
with exact output match.

• ggml: move q4_1_q8_1 WASM SIMD implementation to wasm backend

Relocate the SIMD128 implementation of ggml_vec_dot_q4_1_q8_1 to ggml/src/ggml-cpu/arch/wasm/quants.c to follow architecture-specific layout. Restore the generic implementation in ggml/src/ggml-cpu/quants.c.
Move for loop in the else block.

• ggml: use generic q4_1_q8_1 fallback in wasm backend