Alternatives and similar repositories for triton-cn

Users that are interested in triton-cn are comparing it to the libraries listed below

• gogongxt / nano-sglang
  ☆102Updated this week
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆63Updated last year
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆242Updated last month
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 5 months ago
• madsys-dev / deepseekv2-profile
  ☆153Updated 10 months ago
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆97Updated this week
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆100Updated last year
• InternLM / turbomind
  ☆96Updated 9 months ago
• mdy666 / mdy_triton
  ☆150Updated 6 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆120Updated last year
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆134Updated 4 months ago
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆213Updated 2 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆141Updated 7 months ago
• YuxueYang1204 / CudaDemo
  Implement custom operators in PyTorch with cuda/c++
  ☆76Updated 3 years 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.
  ☆46Updated 6 months ago
• harleyszhang / lite_llama
  A light llama-like llm inference framework based on the triton kernel.
  ☆167Updated 3 months ago
• 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 10 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆153Updated 4 months ago
• pzhao-eng / FlashMLA
  ☆60Updated 5 months ago
• flagos-ai / FlagCX
  FlagCX is a scalable and adaptive cross-chip communication library.
  ☆138Updated this week
• AlibabaPAI / FLASHNN
  ☆104Updated last year
• toyaix / TritonLLM
  LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
  ☆62Updated 2 months ago
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆61Updated last year
• OpenPPL / ppl.llm.serving
  ☆130Updated last year
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆95Updated 3 weeks ago
• AyakaGEMM / Hands-on-GEMM
  ☆144Updated last year
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆132Updated 2 years ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 11 months ago
• OpenPPL / ppl.nn.llm
  ☆141Updated last year
• InfiniTensor / InfiniTensor
  ☆278Updated 2 months ago