Alternatives and similar repositories for neural-speed

Users that are interested in neural-speed are comparing it to the libraries listed below

• neuralmagic / nm-vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆266Updated 11 months ago
• huggingface / optimum-benchmark
  🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of O…
  ☆315Updated last week
• intel / auto-round
  Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
  ☆631Updated this week
• mobiusml / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆878Updated last week
• lapp0 / lm-inference-engines
  Comparison of Language Model Inference Engines
  ☆229Updated 9 months ago
• NetEase-FuXi / EETQ
  Easy and Efficient Quantization for Transformers
  ☆203Updated 2 months ago
• huggingface / optimum-intel
  🤗 Optimum Intel: Accelerate inference with Intel optimization tools
  ☆489Updated this week
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.
  ☆177Updated 5 months ago
• Cornell-RelaxML / quip-sharp
  ☆555Updated 10 months ago
• microsoft / VPTQ
  VPTQ, A Flexible and Extreme low-bit quantization algorithm
  ☆655Updated 4 months ago
• EmbeddedLLM / vllm
  vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆89Updated this week
• npuichigo / openai_trtllm
  OpenAI compatible API for TensorRT LLM triton backend
  ☆214Updated last year
• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆277Updated last year
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆898Updated last year
• neuralmagic / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆157Updated this week
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆155Updated 11 months ago
• neuralmagic / AutoFP8
  ☆199Updated 4 months ago
• likejazz / llama3.cuda
  llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
  ☆343Updated 4 months ago
• mlc-ai / llm-perf-bench
  ☆120Updated last year
• Infini-AI-Lab / Sequoia
  scalable and robust tree-based speculative decoding algorithm
  ☆357Updated 7 months ago
• efeslab / Nanoflow
  A throughput-oriented high-performance serving framework for LLMs
  ☆887Updated last month
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆380Updated last year
• SqueezeAILab / SqueezeLLM
  [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
  ☆704Updated last year
• triton-inference-server / vllm_backend
  ☆296Updated last week
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆307Updated 2 years ago
• mit-han-lab / omniserve
  [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…
  ☆753Updated 6 months ago
• vectorch-ai / ScaleLLM
  A high-performance inference system for large language models, designed for production environments.
  ☆465Updated this week
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆232Updated 10 months ago
• run-ai / llmperf
  ☆59Updated last year
• huggingface / inference-benchmarker
  Inference server benchmarking tool
  ☆100Updated 4 months ago