ggerganov/llama.cpp b9510: b9510
retained text
<details open> 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): | impl | ns/call | speedup | |--------|---------|---------| | scalar | 880.7 | 1.00x | | simd | 257.8 | 3.42x | 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 </details> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-arm64.tar.gz) - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-s390x.tar.gz) - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-vulkan-x64.tar.gz) - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-vulkan-arm64.tar.gz) - [Ubuntu x64 (ROCm 7.2)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-rocm-7.2-x64.tar.gz) - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-ubuntu-openvino-2026.0-x64.tar.gz) - Ubuntu x64 (SYCL FP32) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) **Android:** - [Android arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-android-arm64.tar.gz) **Windows:** - [Windows x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-cpu-x64.zip) - [Windows arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-cpu-arm64.zip) - [Windows x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-cuda-12.4-x64.zip) - [CUDA 12.4 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9510/cudart-llama-bin-win-cuda-12.4-x64.zip) - [Windows x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-cuda-13.3-x64.zip) - [CUDA 13.3 DLLs](https://github.com/ggml-org/llama.cpp/releases/download/b9510/cudart-llama-bin-win-cuda-13.3-x64.zip) - [Windows x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-vulkan-x64.zip) - Windows x64 (SYCL) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - [Windows x64 (HIP)](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-bin-win-hip-radeon-x64.zip) **openEuler:** - [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23705) - openEuler x86 (310p) - openEuler x86 (910b, ACL Graph) - openEuler aarch64 (310p) - openEuler aarch64 (910b, ACL Graph) **UI:** - [UI](https://github.com/ggml-org/llama.cpp/releases/download/b9510/llama-b9510-ui.tar.gz)
document fetched 2026-06-05 09:36