amazon-science / piperag

Related projects ⓘ

Alternatives and complementary repositories for piperag

• hao-ai-lab / MuxServe
  ☆42Updated 5 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆37Updated 3 months ago
• YaoJiayi / CacheBlend
  ☆51Updated last month
• yale-sys / prompt-cache
  Modular and structured prompt caching for low-latency LLM inference
  ☆65Updated this week
• LoongServe / LoongServe
  ☆43Updated last month
• UChi-JCL / CacheGen
  ☆63Updated last month
• Infini-AI-Lab / MagicPIG
  MagicPIG: LSH Sampling for Efficient LLM Generation
  ☆45Updated 2 weeks ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆111Updated last month
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆85Updated 7 months ago
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆86Updated this week
• jiazhihao / attention_superoptimizer
  An Attention Superoptimizer
  ☆20Updated 6 months ago
• WukLab / InferCept
  ☆17Updated 4 months ago
• DerrickYLJ / TidalDecode
  TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆21Updated last month
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆30Updated 3 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆55Updated 2 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆74Updated last year
• MayDomine / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆17Updated 5 months ago
• TorchMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆101Updated 2 months ago
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆29Updated last week
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆178Updated last year
• Hsword / SpotServe
  SpotServe: Serving Generative Large Language Models on Preemptible Instances
  ☆99Updated 8 months ago
• tyler-griggs / melange-release
  ☆36Updated 4 months ago
• zcli-charlie / Awesome-KV-Cache
  ☆36Updated last month
• d-matrix-ai / keyformer-llm
  ☆42Updated 7 months ago
• LiuXiaoxuanPKU / OSD
  ☆34Updated 2 months ago
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆98Updated 4 months ago
• thu-pacman / FasterMoE
  ☆70Updated 2 years ago
• madsys-dev / deepseekv2-profile
  ☆63Updated 3 months ago
• HPMLL / BurstGPT
  A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems
  ☆126Updated 3 weeks ago
• RulinShao / FastCkpt
  Python package for rematerialization-aware gradient checkpointing
  ☆23Updated last year