Alternatives and similar repositories for nano-sglang

Users that are interested in nano-sglang are comparing it to the libraries listed below

• InternLM / turbomind
  ☆97Updated 8 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆45Updated 6 months ago
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆62Updated last year
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆82Updated this week
• flashinfer-ai / cutlass-viz
  ☆65Updated 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.
  ☆235Updated 3 weeks ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆88Updated last week
• AlibabaPAI / FLASHNN
  ☆102Updated last year
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆97Updated 11 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆135Updated 7 months ago
• ByteDance-Seed / cudaLLM
  ☆124Updated 3 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆40Updated last year
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆78Updated last year
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆85Updated this week
• madsys-dev / deepseekv2-profile
  ☆153Updated 9 months ago
• dsl-learn / cutile-learn
  NVIDIA cuTile learn
  ☆69Updated this week
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• CalvinXKY / mfu_calculation
  A simple calculation for LLM MFU.
  ☆50Updated 3 months ago
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆190Updated 10 months ago
• flagos-ai / libtriton_jit
  A Triton JIT runtime and ffi provider in C++
  ☆29Updated 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.
  ☆43Updated 9 months ago
• CalebDu / Awesome-Cute
  ☆112Updated 6 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆194Updated 2 months ago
• Chtholly-Boss / swizzle
  A practical way of learning Swizzle
  ☆36Updated 10 months ago
• hyperai / triton-cn
  Triton Documentation in Chinese Simplified / Triton 中文文档
  ☆95Updated 3 weeks ago
• DD-DuDa / BitDecoding
  [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆66Updated 3 weeks ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆118Updated 6 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆96Updated 3 months ago
• toyaix / TritonLLM
  LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
  ☆60Updated last month