LLMServe / DistServe
Disaggregated serving system for Large Language Models (LLMs).
☆359Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for DistServe
- A low-latency & high-throughput serving engine for LLMs☆245Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆238Updated last week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆311Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆213Updated this week
- A large-scale simulation framework for LLM inference☆277Updated last month
- paper and its code for AI System☆215Updated 2 months ago
- Ultra-Fast and Cheaper Long-Context LLM Inference☆233Updated this week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆357Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆379Updated 3 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
- A fast communication-overlapping library for tensor parallelism on GPUs.☆224Updated 3 weeks ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆342Updated this week
- ☆289Updated 7 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆391Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆142Updated 2 years ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆355Updated last week
- High performance Transformer implementation in C++.☆82Updated 2 months ago
- ☆502Updated 2 months ago
- A throughput-oriented high-performance serving framework for LLMs☆636Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆281Updated last week
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆443Updated last week
- ☆140Updated 6 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆169Updated this week
- ☆52Updated last week
- A PyTorch Native LLM Training Framework☆665Updated 2 months ago
- ☆123Updated 2 weeks ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆45Updated 3 months ago
- nnScaler: Compiling DNN models for Parallel Training☆74Updated 3 weeks ago