NascentCore / llm-numbers-cn
中文版 llm-numbers
☆94Updated 8 months ago
Related projects: ⓘ
- LLM Inference benchmark☆331Updated last month
- ☆105Updated last week
- ☆251Updated last week
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆232Updated 6 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆512Updated last week
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆209Updated this week
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆246Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆129Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆1,045Updated last month
- ☆70Updated 9 months ago
- Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs…☆396Updated last month
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆130Updated 3 weeks ago
- ☆310Updated 2 months ago
- ☆196Updated 4 months ago
- Light local website for displaying performances from different chat models.☆85Updated 10 months ago
- ☆131Updated last week
- 大模型多维度中文对齐评测基准 (ACL 2024)☆293Updated last month
- FlagEval is an evaluation toolkit for AI large foundation models.☆290Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆309Updated this week
- ☆123Updated 3 months ago
- ☆29Updated 3 weeks ago
- ☆148Updated 10 months ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆277Updated this week
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆56Updated last year
- GPT-Fathom is an open-source and reproducible LLM evaluation suite, benchmarking 10+ leading open-source and closed-source LLMs as well a…☆350Updated 5 months ago
- Best practice for training LLaMA models in Megatron-LM☆606Updated 8 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆90Updated 7 months ago
- 更纯粹、更高压缩率的Tokenizer☆438Updated 5 months ago
- Efficient AI Inference & Serving☆452Updated 8 months ago
- Collaborative Training of Large Language Models in an Efficient Way☆405Updated 3 weeks ago