Alternatives and similar repositories for speculative_decoding.c

Users that are interested in speculative_decoding.c are comparing it to the libraries listed below

• salykova / sgemm.cu
  High-Performance FP32 GEMM on CUDA devices
  ☆117Updated last year
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆46Updated 7 months ago
• thomaschlt / mla.c
  Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.
  ☆19Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆95Updated 4 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆93Updated last year
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆32Updated last year
• microsoft / AttentionEngine
  ☆117Updated 8 months ago
• IST-DASLab / Quartet
  ☆118Updated last month
• ACA-Lab-SJTU / token-ring
  ☆13Updated last year
• vedantroy / gpu_kernels
  ☆27Updated 2 years ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated last year
• SqueezeBits / QUICK
  QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
  ☆120Updated last year
• mit-han-lab / tinychat-tutorial
  ☆77Updated last year
• triton-lang / kernels
  ☆104Updated last year
• flashinfer-ai / cutlass-viz
  ☆65Updated 9 months ago
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆260Updated last year
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆165Updated 2 months ago
• casper-hansen / AutoAWQ_kernels
  ☆79Updated last year
• sgl-project / whl
  Kernel Library Wheel for SGLang
  ☆17Updated this week
• Cornell-RelaxML / qtip
  ☆163Updated 7 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆141Updated last year
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆106Updated 7 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆127Updated last year
• INT-FlashAttention2024 / INT-FlashAttention
  ☆85Updated last year
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆99Updated 8 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 9 months ago
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆135Updated last year
• GATECH-EIC / ShiftAddLLM
  ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
  ☆112Updated last year
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆61Updated last year
• TiledTensor / TiledBench
  Benchmark tests supporting the TiledCUDA library.
  ☆18Updated last year