OpenPPL / ppl.nn.llm

Related projects ⓘ

Alternatives and complementary repositories for ppl.nn.llm

• OpenPPL / ppl.llm.serving
  ☆123Updated this week
• OpenPPL / ppl.llm.kernel.cuda
  ☆136Updated this week
• OpenPPL / ppl.pmx
  ☆56Updated this 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.
  ☆26Updated 2 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆97Updated 7 months ago
• AlibabaPAI / FLASHNN
  ☆79Updated 2 months ago
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆60Updated last year
• OpenPPL / ppl.kernel.cuda
  ☆32Updated last month
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆215Updated 5 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆85Updated 8 months ago
• MARD1NO / CUDA-PPT
  ☆79Updated last year
• reed-lau / cute-gemm
  ☆78Updated 8 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆52Updated 3 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆76Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆98Updated 2 months ago
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆200Updated last month
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆82Updated 5 months ago
• bytedance / flux
  A fast communication-overlapping library for tensor parallelism on GPUs.
  ☆219Updated last week
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆226Updated this week
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆74Updated 7 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in Triton Language.
  ☆329Updated this week
• LeiWang1999 / tvm_gpu_gemm
  play gemm with tvm
  ☆84Updated last year
• Bruce-Lee-LY / cuda_hgemm
  Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…
  ☆296Updated 2 months ago
• KnowingNothing / MatmulTutorial
  A Easy-to-understand TensorOp Matmul Tutorial
  ☆288Updated last month
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆32Updated 3 months ago
• ColfaxResearch / cutlass-kernels
  ☆162Updated 4 months ago
• 66RING / tiny-flash-attention
  flash attention tutorial written in python, triton, cuda, cutlass
  ☆195Updated 4 months ago
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆196Updated 2 weeks ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆46Updated 3 months ago
• TiledTensor / TiledCUDA
  TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
  ☆148Updated this week