Alternatives and similar repositories for hydragen:

Users that are interested in hydragen are comparing it to the libraries listed below

• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆77Updated 4 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆71Updated 6 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆66Updated 9 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆110Updated 3 months ago
• triton-lang / kernels
  ☆73Updated 4 months ago
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆37Updated 8 months ago
• sail-sg / VocabularyParallelism
  Vocabulary Parallelism
  ☆17Updated 2 weeks ago
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆208Updated 4 months ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆59Updated 5 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆84Updated 6 months ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆151Updated this week
• RulinShao / LightSeq
  Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers
  ☆207Updated 7 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆73Updated last month
• FasterDecoding / SnapKV
  ☆232Updated 10 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆122Updated 7 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆90Updated last week
• FasterDecoding / TEAL
  ☆118Updated last month
• deepspeedai / DeepSpeed-Kernels
  ☆62Updated last month
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆157Updated 8 months ago
• microsoft / chunk-attention
  ☆65Updated 3 months ago
• microsoft / AttentionEngine
  ☆51Updated 2 weeks ago
• graphcore-research / llm-inference-research
  An experimentation platform for LLM inference optimisation
  ☆29Updated 6 months ago
• thunlp / TritonBench
  TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
  ☆24Updated 3 weeks ago
• tyler-griggs / melange-release
  ☆45Updated 9 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆50Updated 2 weeks ago
• hao-ai-lab / MuxServe
  ☆55Updated 9 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆91Updated last month
• dame-cell / Triformer
  Transformers components but in Triton
  ☆32Updated last week
• thu-pacman / FasterMoE
  ☆81Updated 2 years ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆83Updated this week