NascentCore / llm-numbers-cn
中文版 llm-numbers
☆116Updated last year
Alternatives and similar repositories for llm-numbers-cn:
Users that are interested in llm-numbers-cn are comparing it to the libraries listed below
- LLM Inference benchmark☆377Updated 5 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆88Updated 10 months ago
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆236Updated 10 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆208Updated this week
- ☆302Updated 3 weeks ago
- A flexible and efficient training framework for large-scale alignment tasks☆272Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆582Updated 3 months ago
- ☆76Updated 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…☆348Updated 9 months ago
- ☆71Updated 5 months ago
- 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。☆283Updated 5 months ago
- ☆317Updated 6 months ago
- ☆52Updated last year
- ☆216Updated last year
- ☆127Updated 3 weeks ago
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆230Updated 2 months ago
- ☆151Updated last month
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆47Updated 5 months ago
- Materials for learning SGLang☆166Updated last week
- 怎么训练一个LLM分词器☆137Updated last year
- ☆95Updated 2 months ago
- Light local website for displaying performances from different chat models.☆85Updated last year
- FlagScale is a large model toolkit based on open-sourced projects.☆207Updated this week
- Inference code for LLaMA models☆114Updated last year
- Implement some method of LLM KV Cache Sparsity☆30Updated 7 months ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆92Updated 11 months ago
- ☆161Updated last year
- FlagEval is an evaluation toolkit for AI large foundation models.☆315Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆400Updated 2 weeks ago
- Transformer related optimization, including BERT, GPT☆39Updated last year