Alternatives and similar repositories for llama_cu_awq:

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

• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆99Updated 4 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆88Updated 11 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆94Updated 6 months ago
• AlibabaPAI / FLASHNN
  ☆79Updated 4 months ago
• Bruce-Lee-LY / cuda_hgemv
  Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.
  ☆54Updated 4 months ago
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆34Updated 4 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆53Updated 5 months ago
• yifuwang / symm-mem-recipes
  ☆36Updated last month
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆67Updated last month
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆61Updated 2 months ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆85Updated last year
• CalebDu / Awesome-Cute
  ☆26Updated last week
• ColfaxResearch / cutlass-kernels
  ☆180Updated 6 months ago
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆64Updated 6 years ago
• pytorch-labs / tritonbench
  Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
  ☆86Updated this week
• INT-FlashAttention2024 / INT-FlashAttention
  ☆58Updated last week
• ColfaxResearch / cfx-article-src
  ☆67Updated last month
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆175Updated this week
• DefTruth / hgemm-tensorcores-mma
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆47Updated this week
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated 9 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆232Updated 3 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆95Updated last month
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆132Updated 2 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆17Updated this week
• zeroine / cutlass-cute-sample
  ☆25Updated 9 months ago
• nox-410 / tvm.tl
  An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.
  ☆51Updated 6 months ago
• microsoft / TileFusion
  TileFusion is a highly efficient kernel template library designed to elevate the level of abstraction in CUDA C for processing tiles.
  ☆43Updated this week
• triton-lang / kernels
  ☆64Updated 2 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆27Updated 2 months ago
• jundaf2 / CUDA-INT8-GEMM
  CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API
  ☆27Updated last year