Alternatives and similar repositories for LightSeq

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

• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆233Updated 8 months ago
• yanring / Megatron-MoE-ModelZoo
  Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
  ☆56Updated this week
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆109Updated 2 months ago
• stanford-futuredata / stk
  ☆110Updated 11 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆135Updated last month
• FasterDecoding / SnapKV
  ☆273Updated last month
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆165Updated last year
• FMInference / DejaVu
  ☆332Updated last year
• thu-pacman / FasterMoE
  ☆85Updated 3 years ago
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆372Updated last year
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆321Updated last month
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆124Updated 8 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆227Updated 2 weeks ago
• FasterDecoding / REST
  REST: Retrieval-Based Speculative Decoding, NAACL 2024
  ☆207Updated 8 months ago
• FasterDecoding / TEAL
  ☆139Updated 6 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆319Updated last year
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆109Updated 5 months ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆59Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆104Updated 4 months ago
• ISEEKYAN / mbridge
  Bridge Megatron-Core to Hugging Face/Reinforcement Learning
  ☆93Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆76Updated last year
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆208Updated last week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆80Updated 11 months ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆418Updated 3 months ago
• Dao-AILab / grouped-latent-attention
  ☆123Updated 2 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆201Updated 6 months ago
• lucidrains / speculative-decoding
  Explorations into some recent techniques surrounding speculative decoding
  ☆282Updated 8 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆90Updated 2 years ago
• FMInference / H2O
  [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
  ☆466Updated last year
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆217Updated last year