bytedance / ABQ-LLM

Related projects: ⓘ

• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆46Updated last month
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆82Updated 6 months ago
• AlibabaPAI / FLASHNN
  ☆67Updated last week
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆69Updated 4 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution.
  ☆59Updated last week
• 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.
  ☆20Updated last week
• mit-han-lab / lmquant
  ☆102Updated 3 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆93Updated last week
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆35Updated 4 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆78Updated 4 months ago
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆26Updated this week
• openppl-public / ppl.nn.llm
  ☆140Updated 4 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆41Updated 3 weeks ago
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆81Updated last year
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆46Updated 2 months ago
• OpenPPL / ppl.pmx
  ☆56Updated this week
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated 9 months ago
• naver-aics / lut-gemm
  ☆33Updated 5 months ago
• MARD1NO / CUDA-PPT
  ☆77Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆133Updated 2 months ago
• LeiWang1999 / Stream-k.tvm
  ☆14Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆50Updated 3 months ago
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆81Updated 2 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆114Updated last week
• madsys-dev / deepseekv2-profile
  ☆60Updated last month
• yinuotxie / Efficient-LLM-Inferencing-on-GPUs
  Penn CIS 5650 (GPU Programming and Architecture) Final Project
  ☆21Updated 9 months ago
• MARD1NO / FxxkCUDA
  ☆52Updated this week
• masahi / tvm-cutlass-eval
  ☆34Updated 2 years ago
• microsoft / chunk-attention
  ☆29Updated 4 months ago
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆34Updated 2 months ago