Tencent / AngelSlimLinks
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
☆197Updated this week
Alternatives and similar repositories for AngelSlim
Users that are interested in AngelSlim are comparing it to the libraries listed below
Sorting:
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆201Updated last month
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆249Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆138Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆267Updated 3 months ago
- GLM Series Edge Models☆153Updated 5 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆57Updated 11 months ago
- An industrial extension library of pytorch to accelerate large scale model training☆51Updated 2 months ago
- A quantization algorithm for LLM☆146Updated last year
- 青稞Talk☆160Updated last week
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆59Updated last year
- ☆56Updated last month
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆23Updated last year
- ☆431Updated 3 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆180Updated 7 months ago
- ☆73Updated 5 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆107Updated 7 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆145Updated 2 months ago
- Mixture-of-Experts (MoE) Language Model☆191Updated last year
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆204Updated this week
- KV cache compression for high-throughput LLM inference☆143Updated 9 months ago
- ☆205Updated 6 months ago
- ☆64Updated last week
- Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.☆217Updated last month
- simplify >2GB large onnx model☆64Updated 11 months ago
- ☆72Updated 2 weeks ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆308Updated 5 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆404Updated this week
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆231Updated 5 months ago
- a toolkit on knowledge distillation for large language models☆195Updated last week