Alternatives and similar repositories for concopilot

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

• woct0rdho / transformers-qwen3-moe-fused
  Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
  ☆122Updated this week
• GeeeekExplorer / transformers-patch
  patches for huggingface transformers to save memory
  ☆26Updated last month
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆135Updated last year
• JerryYin777 / PaperHelper
  PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant with Reliable References
  ☆17Updated last year
• NJUDeepEngine / CAEF
  Code for paper: "Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines"
  ☆11Updated 9 months ago
• tile-ai / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆19Updated last week
• vllm-project / vllm-nccl
  Manages vllm-nccl dependency
  ☆17Updated last year
• thunlp / APB
  Official Implementation of APB (ACL 2025 main Oral)
  ☆29Updated 4 months ago
• Infini-AI-Lab / gsm_infinite
  ☆48Updated last month
• Aegis1863 / LLMs-Distillation-Quantification
  Repo of ACL 2025 main Paper "Quantification of Large Language Model Distillation"
  ☆88Updated last month
• FreedomIntelligence / FastLLM
  Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];
  ☆40Updated last year
• OpenNLPLab / LASP
  Linear Attention Sequence Parallelism (LASP)
  ☆85Updated last year
• OpenBMB / CPM.cu
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…
  ☆161Updated last week
• tile-ai / TileOPs
  ☆42Updated this week
• moonquest-ai / SRDA
  ☆28Updated last month
• Tencent-Hunyuan / Tencent-Hunyuan-7B-0124
  ☆19Updated last week
• dame-cell / Triformer
  Transformers components but in Triton
  ☆34Updated 2 months ago
• xverse-ai / XVERSE-MoE-A36B
  XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.
  ☆39Updated 10 months ago
• secsilm / chinese-tokens-in-tiktoken
  Chinese tokens in tiktoken tokenizers.
  ☆31Updated last year
• codefuse-ai / CodeFuse-MFT-VLM
  ☆39Updated 9 months ago
• xverse-ai / XVERSE-MoE-A4.2B
  XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.
  ☆39Updated last year
• multimodal-art-projection / COIG-P
  ☆38Updated this week
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆42Updated 2 weeks ago
• hpcaitech / CachedEmbedding
  A memory efficient DLRM training solution using ColossalAI
  ☆105Updated 2 years ago
• rayleizhu / vllm-ra
  [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts
  ☆40Updated last year
• inclusionAI / Ring
  Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.
  ☆87Updated 3 weeks ago
• Harry-Chen / InfMoE
  Inference framework for MoE layers based on TensorRT with Python binding
  ☆41Updated 4 years ago
• Ascend / AscendSpeed
  ☆79Updated last year
• codefuse-ai / Collinear-Constrained-Attention
  ☆63Updated last year
• StarRing2022 / R1-Nature
  最简易的R1结果在小模型上的复现，阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证，对于强推理能力，think思考过程性内容是AGI/ASI的核心。
  ☆45Updated 5 months ago