powerserve-project / PowerServeLinks
High-speed and easy-use LLM serving framework for local deployment
☆141Updated 5 months ago
Alternatives and similar repositories for PowerServe
Users that are interested in PowerServe 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…☆219Updated last week
- Bamboo-7B Large Language Model☆93Updated last year
- KV cache compression for high-throughput LLM inference☆149Updated 11 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆255Updated last year
- [EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models☆68Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Updated 5 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆96Updated last month
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆306Updated 7 months ago
- ☆163Updated 7 months ago
- Fast and memory-efficient exact attention☆109Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆333Updated last year
- Fast OS-level support for GPU checkpoint and restore☆269Updated 3 months ago
- ☆171Updated 3 weeks ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆326Updated last month
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆802Updated 10 months ago
- The homepage of OneBit model quantization framework.☆199Updated 11 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆275Updated 3 months ago
- Modular and structured prompt caching for low-latency LLM inference☆110Updated last year
- ☆48Updated last year
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆31Updated last year
- LLM Inference on consumer devices☆128Updated 10 months ago
- High performance Transformer implementation in C++.☆148Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆527Updated 3 weeks ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆234Updated this week
- Easy, Fast, and Scalable Multimodal AI☆92Updated this week
- Serverless LLM Serving for Everyone.☆634Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 7 months ago
- ☆340Updated 2 weeks ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆673Updated 8 months ago
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆107Updated 3 weeks ago