AlibabaPAI / llumnixLinks
Efficient and easy multi-instance LLM serving
☆497Updated last month
Alternatives and similar repositories for llumnix
Users that are interested in llumnix are comparing it to the libraries listed below
Sorting:
- A low-latency & high-throughput serving engine for LLMs☆431Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆706Updated 6 months ago
- KV cache store for distributed LLM inference☆345Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆673Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆481Updated 6 months ago
- Ultra and Unified CCL☆595Updated this week
- A large-scale simulation framework for LLM inference☆459Updated 2 months ago
- Perplexity GPU Kernels☆497Updated last month
- Materials for learning SGLang☆615Updated 3 weeks ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆278Updated 7 months ago
- ☆307Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆428Updated last week
- High performance Transformer implementation in C++.☆135Updated 9 months ago
- Stateful LLM Serving☆86Updated 7 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆567Updated last year
- Serverless LLM Serving for Everyone.☆561Updated this week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆904Updated last month
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆112Updated 5 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆213Updated 2 months ago
- A PyTorch Native LLM Training Framework☆875Updated last month
- Zero Bubble Pipeline Parallelism☆432Updated 5 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆220Updated this week
- ☆141Updated 3 months ago
- ☆124Updated 11 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆425Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆278Updated 4 months ago
- DeepSeek-V3/R1 inference performance simulator☆170Updated 6 months ago
- Allow torch tensor memory to be released and resumed later☆150Updated this week
- A lightweight design for computation-communication overlap.☆181Updated last week