pcg-mlp / KsanaLLM
☆322Updated 2 months ago
Alternatives and similar repositories for KsanaLLM:
Users that are interested in KsanaLLM are comparing it to the libraries listed below
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆660Updated last month
- Disaggregated serving system for Large Language Models (LLMs).☆495Updated 7 months ago
- GLake: optimizing GPU memory management and IO transmission.☆436Updated 3 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆246Updated last week
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆237Updated last week
- ☆127Updated 2 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆469Updated last year
- Materials for learning SGLang☆335Updated 3 weeks ago
- FlagPerf is an open-source software platform for benchmarking AI chips.☆324Updated last month
- ☆139Updated 10 months ago
- LLM Inference benchmark☆401Updated 7 months ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆453Updated this week
- ☆124Updated 2 weeks ago
- A flexible and efficient training framework for large-scale alignment tasks☆331Updated last month
- Efficient and easy multi-instance LLM serving☆332Updated this week
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆51Updated 7 months ago
- A self-learning tutorail for CUDA High Performance Programing.☆446Updated 2 weeks ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.☆267Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆310Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆766Updated 5 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆413Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆447Updated last month
- how to learn PyTorch and OneFlow☆406Updated 11 months ago
- ☆145Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆370Updated 2 weeks ago
- Best practice for training LLaMA models in Megatron-LM☆643Updated last year
- A low-latency & high-throughput serving engine for LLMs☆319Updated last month
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆226Updated last week