Alternatives and similar repositories for SmallThinker

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

• inclusionAI / dInfer
  dInfer: An Efficient Inference Framework for Diffusion Language Models
  ☆410Updated last month
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆225Updated 3 weeks ago
• microsoft / AttentionEngine
  ☆118Updated 8 months ago
• deepseek-ai / LPLB
  An early research stage expert-parallel load balancer for MoE models based on linear programming.
  ☆495Updated 2 months ago
• moonquest-ai / SRDA
  ☆30Updated 8 months ago
• wdlctc / headinfer
  ☆64Updated 8 months ago
• NVlabs / QeRL
  QeRL enables RL for 32B LLMs on a single H100 GPU.
  ☆481Updated 2 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆101Updated last month
• TransferQueue / TransferQueue
  [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…
  ☆13Updated 3 weeks ago
• RLsys-Foundation / TritonForge
  🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…
  ☆116Updated 2 months ago
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆155Updated 3 weeks ago
• pangu-tech / pangu-ultra
  ☆74Updated 8 months ago
• inclusionAI / Ring-V2
  Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.
  ☆90Updated 3 months ago
• hao-ai-lab / DistCA
  Efficient Long-context Language Model Training by Core Attention Disaggregation
  ☆87Updated last week
• tile-ai / AttentionEngine
  ☆52Updated 8 months ago
• IST-DASLab / Quartet
  ☆118Updated last month
• Tencent / llm.hunyuan.T1
  ☆82Updated 10 months ago
• PKULab1806 / Fairy-plus-minus-i
  Fairy±i (iFairy): Complex-valued Quantization Framework for Large Language Models
  ☆118Updated 2 months ago
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆220Updated 8 months ago
• JarvisPei / CMoE
  Implementation for the paper: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
  ☆34Updated 11 months ago
• hao-ai-lab / LookaheadReasoning
  [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning
  ☆63Updated 3 months ago
• powerserve-project / PowerServe
  High-speed and easy-use LLM serving framework for local deployment
  ☆146Updated 6 months ago
• argonne-lcf / LLM-Inference-Bench
  LLM-Inference-Bench
  ☆58Updated 6 months ago
• Infini-AI-Lab / Multiverse
  ☆111Updated 4 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆92Updated 2 weeks ago
• zenrran4nlp / Awesome-LLM-Inference-Serving
  ☆47Updated 9 months ago
• NoakLiu / PiKV
  PiKV: KV Cache Management System for Mixture of Experts [Efficient ML System]
  ☆48Updated 3 months ago
• snu-mllab / KVzip
  [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
  ☆196Updated 3 weeks ago
• woct0rdho / transformers-qwen3-moe-fused
  Fused Qwen3 MoE layer for faster training, compatible with Transformers, LoRA, bnb 4-bit quant, Unsloth. Also possible to train LoRA over…
  ☆231Updated this week
• inclusionAI / Ring
  Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
  ☆106Updated 6 months ago