avx2 repositories
Trending repositories tagged avx2, ranked by trending score. Updated daily.
-
1
FareedKhan-dev/kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
GitHub · C · 12,510 stars · 1,935 forks · +127 stars in 24 hours · Trending score 4.17
-
2
l3tchupkt/adaptq
High-performance C++17 KV cache compression engine for LLM inference with Python bindings, SIMD acceleration, and multi-backend support.
GitHub · C++ · 32 stars · 49 forks · +25 stars in 24 hours · Trending score 2.71
-
3
simdjson/simdjson
Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
GitHub · C++ · 24,591 stars · 1,366 forks · +23 stars in 24 hours · Trending score 2.42
-
4
MoeForge/moego
A collection of optimized Go packages for performance-critical code paths.
GitHub · Go · 143 stars · 11 forks · +20 stars in 24 hours · Trending score 2.37
-
5
sergqwer/strata-nvfp4
Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants (huihui abliterated, OrcaRouter) from Hugging Face. CPU experts on AVX-512 or AVX2 (+AVX-VNNI), all experts in RAM from 92 GB, a low-RAM mode below, vision, W4A8 prompts. Windows / CUDA 13.
GitHub · C++ · 251 stars · 31 forks · +2 stars in 24 hours · Trending score 1.47
-
6
mattn/tensai
A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)
GitHub · Go · 120 stars · 6 forks · +8 stars in 24 hours · Trending score 1.43
-
7
prabanta-dev/janas
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
GitHub · C · 735 stars · 73 forks · 0 stars in 24 hours · Trending score 1.28
-
8
OpenNMT/CTranslate2
Fast inference engine for Transformer models
GitHub · C++ · 4,758 stars · 562 forks · +1 stars in 24 hours · Trending score 1.12
-
9
google/highway
Performance-portable, length-agnostic SIMD with runtime dispatch
GitHub · C++ · 5,985 stars · 500 forks · −1 stars in 24 hours · Trending score 0.97
-
10
sdcb/SimdCodecs
Pure-managed, SIMD-accelerated image codecs for .NET: JPEG, PNG, WebP, TIFF, GIF, JPEG 2000 and JBIG2, plus EXIF and ICC. No native dependencies, NativeAOT-compatible; the JPEG decoder beats libjpeg-turbo on our benchmark corpus.
GitHub · C# · 143 stars · 17 forks · 0 stars in 24 hours · Trending score 0.79
-
11
numpy/x86-simd-sort
C++ template library for high performance SIMD based sorting algorithms
GitHub · C++ · 1,036 stars · 78 forks · 0 stars in 24 hours · Trending score 0.71
-
12
simdutf/simdutf
Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension, LoongArch64, POWER. Part of Node.js, WebKit/Safari, Ladybird, Chromium, Cloudflare Workers, Ghostty and Bun.
GitHub · C++ · 2,025 stars · 165 forks · 0 stars in 24 hours · Trending score 0.65
-
13
rust-seq/simd-minimizers
A SIMD-accelerated library to compute random minimizers
GitHub · Rust · 50 stars · 9 forks · +1 stars in 24 hours · Trending score 0.52
-
14
jfalcou/eve
Expressive Vector Engine - SIMD in C++ Goes Brrrr
GitHub · C++ · 1,371 stars · 77 forks · −2 stars in 24 hours · Trending score 0.24
-
15
Sir-Irk/si_normalmap
Simple Single Header Normal Map Generator
GitHub · C · 17 stars · 3 forks · 0 stars in 24 hours · Trending score 0.22
-
16
benmaster82/Pithos
A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a terminal agent, all in one executable.
GitHub · C · 32 stars · 3 forks · 0 stars in 24 hours · Trending score 0.20
-
17
wasif-exe/Apex-Wire
Apex-Wire V6: Production-grade NASDAQ ITCH 5.0 replay engine — per-symbol LOB sharding, synthetic matching engine, MoldUDP64/SoupBinTCP live feed ingestion, LRU eviction, 127.75M msg/s single-core / 509M msg/s multi-core on Sapphire Rapids (47x improvement over V5). 32 crates, 115 tests.
GitHub · Rust · 9 stars · 3 forks · 0 stars in 24 hours · Trending score 0.20
-
18
microsoft/DirectXMath
DirectXMath is an all inline SIMD C++ linear algebra library for use in games and graphics apps
GitHub · C++ · 1,821 stars · 267 forks · 0 stars in 24 hours · Trending score 0.17
-
19
siris9476/pulsarforge
GitHub · C · 24 stars · 4 forks · 0 stars in 24 hours · Trending score 0.14
-
20
nihilai-collective/Jsonifier
A few classes for extremely fast json parsing/serializing in modern C++. Possibly the fastest json parser in C++. Possibly the fastest json serializer in C++.
GitHub · C++ · 103 stars · 7 forks · 0 stars in 24 hours · Trending score 0.10
-
21
WojciechMula/base64simd
Base64 coding and decoding with SIMD instructions (SSE/AVX2/AVX512F/AVX512BW/AVX512VBMI/ARM Neon)
GitHub · C++ · 173 stars · 18 forks · 0 stars in 24 hours · Trending score 0.10
-
22
awxkee/pic-scale
High performance image scale in pure Rust
GitHub · Rust · 45 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08
-
23
Classevelabs/rai
Run language models on your own computer's CPU: one-step installers for Windows, macOS and Linux, a local chat page and API, 4-bit models, pure Rust. No GPU, no Python, nothing leaves your machine.
GitHub · Rust · 16 stars · 1 forks · 0 stars in 24 hours · Trending score 0.08
-
24
MarbleAmongHail/respocket-3DP
The Implementation of The Ledger of Things Node. Layer 1 decentralized blockchain platform for the tokenization of objects. Proof of Scan protocol. Useful smart-contracts and dApps.
GitHub · HTML · 21 stars · 0 forks · 0 stars in 24 hours · Trending score 0.05