thu-pacman / chituLinks
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
☆1,129Updated this week
Alternatives and similar repositories for chitu
Users that are interested in chitu are comparing it to the libraries listed below
Sorting:
- Community maintained hardware plugin for vLLM on Ascend☆703Updated this week
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,076Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,350Updated this week
- run DeepSeek-R1 GGUFs on KTransformers☆231Updated 2 months ago
- An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to infer…☆689Updated 2 months ago
- 一种任务级GPU算力分时调度的高性能深度学习训练平台☆647Updated last year
- Distributed RL System for LLM Reasoning☆1,284Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆777Updated 2 weeks ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,781Updated last month
- FlashInfer: Kernel Library for LLM Serving☆3,088Updated this week
- DeepSeek 系列工作解读、扩展和复现。☆652Updated 2 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆956Updated this week
- ☆132Updated 3 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆253Updated this week
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆774Updated last week
- Expert Parallelism Load Balancer☆1,203Updated 2 months ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆476Updated this week
- Analyze computation-communication overlap in V3/R1.☆1,046Updated 2 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,113Updated this week
- ☆310Updated 5 months ago
- ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents☆479Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆280Updated this week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,792Updated 2 months ago
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆369Updated this week
- Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…☆3,042Updated this week
- Fast, Flexible and Portable Structured Generation☆980Updated last week
- ☆773Updated last month
- LLM Inference benchmark☆419Updated 10 months ago
- GLake: optimizing GPU memory management and IO transmission.☆463Updated 2 months ago
- ☆681Updated this week