Alternatives and similar repositories for llama.cpp-npu

Users that are interested in llama.cpp-npu are comparing it to the libraries listed below

• haozixu / htp-ops-lib
  Self-implemented NN operators for Qualcomm's Hexagon NPU
  ☆34Updated 2 months ago
• ARM-software / kleidiai
  This repository is a read-only mirror of https://gitlab.arm.com/kleidi/kleidiai
  ☆106Updated last week
• xxxxyu / FlexNN
  Code for ACM MobiCom 2024 paper "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices"
  ☆57Updated 10 months ago
• MollySophia / rwkv-qualcomm
  Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK
  ☆89Updated 2 weeks ago
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆200Updated 3 weeks ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆151Updated 4 months ago
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆146Updated last year
• mlc-ai / relax
  ☆171Updated last week
• jeffzhou2000 / ggml-hexagon
  the original reference implementation of a specified llama.cpp backend for Qualcomm Hexagon NPU on Android phone, https://github.com/ggml…
  ☆35Updated 5 months ago
• OpenPPL / ppl.pmx
  ☆60Updated last year
• microsoft / BitBLAS
  BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
  ☆732Updated 4 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 5 months ago
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆51Updated last year
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆239Updated last month
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆276Updated 5 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆110Updated 8 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆123Updated last year
• chraac / llama.cpp
  LLM inference in C/C++
  ☆48Updated this week
• INT-FlashAttention2024 / INT-FlashAttention
  ☆83Updated 10 months ago
• Qualcomm-AI-research / FP8-quantization
  ☆168Updated 2 years ago
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• OpenBitSys / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆131Updated last year
• Guangxuan-Xiao / torch-int
  This repository contains integer operators on GPUs for PyTorch.
  ☆223Updated 2 years ago
• thu-nics / qllm-eval
  Code Repository of Evaluating Quantized Large Language Models
  ☆137Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 3 months ago
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆103Updated 7 years ago
• MegEngine / mperf
  mperf是一个面向移动/嵌入式平台的算子性能调优工具箱
  ☆192Updated 2 years ago
• BrotherHappy / OSTQuant
  [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…
  ☆86Updated 8 months ago
• AlibabaPAI / FLASHNN
  ☆103Updated last year
• ByteDance-Seed / cudaLLM
  ☆125Updated 4 months ago