Alternatives and similar repositories for tinychat-tutorial

Users that are interested in tinychat-tutorial are comparing it to the libraries listed below

• INT-FlashAttention2024 / INT-FlashAttention
  ☆81Updated 7 months ago
• 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.
  ☆40Updated 2 months ago
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆71Updated last month
• ByteDance-Seed / cudaLLM
  ☆99Updated 2 weeks ago
• mit-han-lab / parallel-computing-tutorial
  ☆172Updated 2 years ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆113Updated last year
• microsoft / AttentionEngine
  ☆92Updated 3 months ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆54Updated 7 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆211Updated 3 weeks ago
• ruikangliu / FlatQuant
  [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"
  ☆156Updated last month
• flashinfer-ai / cutlass-viz
  ☆63Updated 4 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• xxyux / SpInfer
  SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs
  ☆55Updated 5 months ago
• Raincleared-Song / sparse_gpu_operator
  GPU operators for sparse tensor operations
  ☆34Updated last year
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 9 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆107Updated 3 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆95Updated 2 months ago
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆148Updated 3 months ago
• InternLM / turbomind
  ☆92Updated 5 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆95Updated 8 months ago
• Qualcomm-AI-research / FP8-quantization
  ☆158Updated 2 years ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆261Updated last month
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆224Updated last year
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆120Updated last year
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆57Updated 3 weeks ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆110Updated 11 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆81Updated last week
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆319Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆138Updated last week
• GATECH-EIC / ShiftAddLLM
  ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
  ☆110Updated 10 months ago