Alternatives and similar repositories for ppl.nn.llm

Users that are interested in ppl.nn.llm are comparing it to the libraries listed below

• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated last year
• OpenPPL / ppl.llm.serving
  ☆130Updated last year
• OpenPPL / ppl.pmx
  ☆60Updated last year
• 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.
  ☆44Updated 11 months ago
• AlibabaPAI / FLASHNN
  ☆105Updated last year
• AyakaGEMM / Hands-on-GEMM
  ☆145Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 4 months ago
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated 2 years ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆78Updated last year
• OpenPPL / ppl.kernel.cuda
  ☆38Updated last year
• MARD1NO / CUDA-PPT
  ☆118Updated 10 months ago
• flagos-ai / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆287Updated last year
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆477Updated last year
• madsys-dev / deepseekv2-profile
  ☆155Updated 11 months ago
• pzhao-eng / FlashMLA
  ☆61Updated 6 months ago
• CalebDu / Awesome-Cute
  ☆113Updated 8 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆110Updated 10 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆114Updated last year
• weishengying / tiny-flash-attention
  使用 cutlass 实现 flash-attention 精简版，具有教学意义
  ☆54Updated last year
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆105Updated 7 years ago
• reed-lau / cute-gemm
  ☆161Updated 3 months ago
• weishengying / cute_gemm
  ☆21Updated last year
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆64Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆115Updated 6 months ago
• kwai / Megatron-Kwai
  LLM training technologies developed by kwai
  ☆70Updated 2 weeks ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆154Updated 5 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆270Updated 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.
  ☆250Updated this week
• zeroine / cutlass-cute-sample
  ☆49Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆120Updated last year