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
• thomaschlt / mla.c
  Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.
  ☆19Updated last year
• mit-han-lab / tinychat-tutorial
  ☆77Updated 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
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆95Updated 4 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆127Updated last year
• vedantroy / gpu_kernels
  ☆27Updated 2 years ago
• triton-lang / kernels
  ☆104Updated last year
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆260Updated last year
• flashinfer-ai / cutlass-viz
  ☆65Updated 9 months ago
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆165Updated 2 months ago
• TiledTensor / TiledBench
  Benchmark tests supporting the TiledCUDA library.
  ☆18Updated last year
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• AutonomicPerfectionist / PipeInfer
  PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
  ☆32Updated last year
• NTT123 / cute-viz
  Cute layout visualization
  ☆29Updated 3 weeks ago
• meta-pytorch / triton-cpu
  An experimental CPU backend for Triton (https//github.com/openai/triton)
  ☆49Updated 5 months ago
• moritztng / grayskull-attention
  Attention in SRAM on Tenstorrent Grayskull
  ☆40Updated last year
• tile-ai / AttentionEngine
  ☆52Updated 8 months ago
• tspeterkim / paged-attention-minimal
  a minimal cache manager for PagedAttention, on top of llama3.
  ☆135Updated last year
• ademeure / cuda-side-boost
  ☆53Updated 9 months ago
• 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
• ScalingIntelligence / good-kernels
  Samples of good AI generated CUDA kernels
  ☆99Updated 8 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆165Updated last year
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆73Updated 9 months ago
• microsoft / AttentionEngine
  ☆118Updated 8 months ago
• sgl-project / whl
  Kernel Library Wheel for SGLang
  ☆17Updated last week
• gpu-mode / popcorn-cli
  ☆95Updated this week
• ACA-Lab-SJTU / token-ring
  ☆13Updated last year
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆93Updated last year