microsoft / sarathi-serve
A low-latency & high-throughput serving engine for LLMs
☆245Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for sarathi-serve
- Dynamic Memory Management for Serving LLMs without PagedAttention☆238Updated last week
- A large-scale simulation framework for LLM inference☆277Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆359Updated 3 months ago
- Efficient and easy multi-instance LLM serving☆213Updated this week
- Ultra-Fast and Cheaper Long-Context LLM Inference☆233Updated this week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆311Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆175Updated 2 weeks ago
- High performance Transformer implementation in C++.☆82Updated 2 months ago
- Materials for learning SGLang☆96Updated this week
- ☆52Updated last week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆202Updated 2 weeks ago
- paper and its code for AI System☆215Updated 2 months ago
- A fast communication-overlapping library for tensor parallelism on GPUs.☆224Updated 3 weeks ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆180Updated last year
- ☆51Updated last month
- ☆289Updated 7 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆355Updated last week
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆208Updated 3 weeks ago
- ☆167Updated 4 months ago
- nnScaler: Compiling DNN models for Parallel Training☆74Updated 3 weeks ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- Summary of some awesome work for optimizing LLM inference☆37Updated 2 weeks ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆104Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆281Updated last week
- ☆70Updated 2 years ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆87Updated last month
- ☆79Updated 2 months ago