zhaochenyang20 / ModelServerLinks
Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
☆61Updated last year
Alternatives and similar repositories for ModelServer
Users that are interested in ModelServer 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…☆225Updated 3 weeks ago
- ☆96Updated 10 months ago
- ☆155Updated 11 months ago
- vLLM Router☆54Updated last year
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆251Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆139Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Updated last month
- ☆206Updated 9 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆120Updated last year
- A quantization algorithm for LLM☆148Updated last year
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆99Updated 5 months ago
- ☆79Updated 2 years ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆110Updated 10 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Updated 5 months ago
- ☆79Updated last year
- ☆85Updated 9 months ago
- Pipeline-Parallel Lecture: Simplest Dualpipe Implementation.☆31Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆141Updated last year
- KV cache compression for high-throughput LLM inference☆151Updated last year
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆46Updated 7 months ago
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆250Updated this week
- ☆117Updated 3 weeks ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆274Updated 6 months ago
- Fast and memory-efficient exact attention☆111Updated last week
- Distributed IO-aware Attention algorithm☆23Updated 4 months ago
- ☆16Updated last year
- Triton implementation of Flash Attention2.0☆49Updated 2 years ago
- ☆130Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆55Updated last year
- patches for huggingface transformers to save memory☆33Updated 8 months ago