Alternatives and similar repositories for turbomind

Users that are interested in turbomind are comparing it to the libraries listed below

• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆223Updated 2 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆124Updated 4 months ago
• flashinfer-ai / cutlass-viz
  ☆65Updated 5 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆121Updated 5 months ago
• AlibabaPAI / FLASHNN
  ☆100Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆107Updated 6 months ago
• madsys-dev / deepseekv2-profile
  ☆148Updated 7 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.
  ☆41Updated 7 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆144Updated 2 months ago
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆112Updated last year
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆72Updated 5 months ago
• microsoft / AttentionEngine
  ☆101Updated 5 months ago
• ByteDance-Seed / cudaLLM
  ☆120Updated 2 months ago
• InternLM / Awesome-LLM-Training-System
  ☆43Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆115Updated last year
• 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 4 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆320Updated last year
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆265Updated 3 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆282Updated last year
• microsoft / chunk-attention
  ☆78Updated 6 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆50Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated last month
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆96Updated this week
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆96Updated 10 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆130Updated 10 months ago
• neuralmagic / AutoFP8
  ☆205Updated 5 months ago
• sgl-project / sglang-jax
  JAX backend for SGL
  ☆77Updated last week
• CalebDu / Awesome-Cute
  ☆107Updated 5 months ago
• fzyzcjy / torch_utils
  Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)
  ☆59Updated last month
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆221Updated 2 years ago