zhaochenyang20 / ModelServerLinks
Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
☆53Updated 7 months ago
Alternatives and similar repositories for ModelServer
Users that are interested in ModelServer are comparing it to the libraries listed below
Sorting:
- ☆86Updated 2 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- ☆141Updated 3 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆129Updated this week
- An easy-to-use package for implementing SmoothQuant for LLMs☆100Updated 2 months ago
- ☆77Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆133Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆38Updated last week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆89Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆242Updated last year
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 3 months ago
- ☆96Updated 9 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆128Updated 2 months ago
- A simple calculation for LLM MFU.☆38Updated 3 months ago
- ☆60Updated last month
- ☆137Updated last month
- ☆194Updated last month
- ☆79Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆54Updated last week
- Manages vllm-nccl dependency☆17Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆115Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated 11 months ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- ☆54Updated last year
- Fast and memory-efficient exact attention☆74Updated last week
- ☆256Updated last year
- ☆16Updated last year