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.
  ☆263Updated 4 months ago
• yanring / Megatron-MoE-ModelZoo
  Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
  ☆161Updated 3 weeks ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆184Updated last month
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆143Updated 8 months ago
• stanford-futuredata / stk
  ☆115Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆176Updated last year
• thu-pacman / FasterMoE
  ☆89Updated 3 years ago
• FasterDecoding / SnapKV
  ☆303Updated 7 months ago
• ISEEKYAN / mbridge
  Bridge Megatron-Core to Hugging Face/Reinforcement Learning
  ☆193Updated this week
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆142Updated last year
• FasterDecoding / REST
  REST: Retrieval-Based Speculative Decoding, NAACL 2024
  ☆214Updated 5 months ago
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆404Updated last year
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆258Updated 6 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆372Updated 7 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆336Updated last year
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆65Updated last year
• foundation-model-stack / foundation-model-stack
  🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
  ☆219Updated last week
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆93Updated last year
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆449Updated 9 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆114Updated 10 months ago
• FasterDecoding / TEAL
  ☆158Updated 11 months ago
• FMInference / DejaVu
  ☆352Updated last year
• Dao-AILab / sonic-moe
  Accelerating MoE with IO and Tile-aware Optimizations
  ☆583Updated last week
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆214Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆110Updated 10 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆79Updated last year
• flagos-ai / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆287Updated last year
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆233Updated 2 years ago
• NVIDIA-NeMo / Megatron-Bridge
  Training library for Megatron-based models with bidirectional Hugging Face conversion capability
  ☆419Updated this week
• zankner / Hydra
  ☆51Updated last year