Alternatives and similar repositories for sgl-kernel-npu

Users that are interested in sgl-kernel-npu are comparing it to the libraries listed below

• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆325Updated this week
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆105Updated 3 months ago
• pprp / ultrascale-playbook-zh
  UltraScale Playbook 中文版
  ☆68Updated 5 months ago
• DeepLink-org / DIOPI
  ☆73Updated 9 months ago
• sihyeong / Awesome-LLM-Inference-Engine
  ☆121Updated 2 months ago
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆80Updated 4 months ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆103Updated last month
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆530Updated last month
• sunkx109 / GPUs-Specs
  Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM
  ☆62Updated 2 weeks 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 2 weeks ago
• madsys-dev / deepseekv2-profile
  ☆146Updated 5 months ago
• stepfun-ai / StepMesh
  ☆279Updated last week
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆346Updated last week
• DeepLink-org / dlinfer
  ☆54Updated last week
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆165Updated 4 months ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆61Updated last year
• SiriusNEO / Triton-Puzzles-Lite
  Puzzles for learning Triton, play it with minimal environment configuration!
  ☆489Updated 8 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆111Updated last year
• Tencent / KsanaLLM
  ☆483Updated 2 weeks ago
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆147Updated 2 weeks ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆129Updated 7 months ago
• perplexityai / pplx-kernels
  Perplexity GPU Kernels
  ☆444Updated 2 weeks ago
• pzhao-eng / FlashMLA
  ☆53Updated last month
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆60Updated 9 months ago
• InternLM / turbomind
  ☆92Updated 5 months ago
• AlibabaPAI / FLASHNN
  ☆97Updated 11 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆157Updated last week
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆655Updated this week
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆219Updated last month
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆94Updated 8 months ago