Alternatives and similar repositories for llm-inference

Users that are interested in llm-inference are comparing it to the libraries listed below

• NetEase-FuXi / EETQ
  Easy and Efficient Quantization for Transformers
  ☆198Updated last month
• inferflow / inferflow
  Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
  ☆244Updated last year
• anyscale / llm-continuous-batching-benchmarks
  ☆120Updated last year
• fw-ai / benchmark
  Benchmark suite for LLMs from Fireworks.ai
  ☆76Updated last week
• neuralmagic / AutoFP8
  ☆195Updated 2 months ago
• intel / llm-on-ray
  Pretrain, finetune and serve LLMs on Intel platforms with Ray
  ☆128Updated 2 weeks ago
• casper-hansen / AutoAWQ_kernels
  ☆76Updated 7 months ago
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆54Updated 8 months ago
• LLM-inference-router / vllm-router
  vLLM Router
  ☆39Updated last year
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆135Updated last year
• bentoml / llm-bench
  ☆55Updated 8 months ago
• microsoft / batch-inference
  Dynamic batching library for Deep Learning inference. Tutorials for LLM, GPT scenarios.
  ☆100Updated 11 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆81Updated 2 weeks ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.
  ☆174Updated 3 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• thu-ml / low-bit-optimizers
  Low-bit optimizers for PyTorch
  ☆130Updated last year
• InternLM / turbomind
  ☆90Updated 3 months ago
• jaymody / speculative-sampling
  Simple implementation of Speculative Sampling in NumPy for GPT-2.
  ☆95Updated last year
• neuralmagic / nm-vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆265Updated 9 months ago
• kyegomez / FlashAttention20
  Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels
  ☆105Updated last year
• vectorch-ai / ScaleLLM
  A high-performance inference system for large language models, designed for production environments.
  ☆456Updated this week
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆207Updated last week
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆302Updated 2 years ago
• Dao-AILab / grouped-latent-attention
  ☆122Updated last month
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆64Updated 2 years ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆102Updated 3 months ago
• triton-inference-server / vllm_backend
  ☆275Updated last month
• shreyansh26 / Speculative-Sampling
  Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
  ☆98Updated last year
• nbasyl / LLM-FP4
  The official implementation of the EMNLP 2023 paper LLM-FP4
  ☆210Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆122Updated 7 months ago