thu-pacman / chituLinks
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
☆1,261Updated 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☆1,092Updated this week
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,654Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,912Updated this week
- run DeepSeek-R1 GGUFs on KTransformers☆251Updated 6 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☆695Updated last year
- ☆491Updated last month
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆847Updated last month
- ☆327Updated last month
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆264Updated last month
- Analyze computation-communication overlap in V3/R1.☆1,097Updated 5 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆352Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,106Updated 2 weeks ago
- An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to infer…☆754Updated 6 months ago
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆426Updated this week
- Expert Parallelism Load Balancer☆1,263Updated 5 months ago
- Distributed RL System for LLM Reasoning☆2,569Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,899Updated 5 months ago
- ☆958Updated last week
- LLM 并发性能测试工具,支持自动化压力测试和性能报告生成。☆155Updated 5 months ago
- LLM Inference benchmark☆426Updated last year
- Low-bit LLM inference on CPU/NPU with lookup table☆852Updated 3 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,341Updated this week
- ☆427Updated 3 weeks ago
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆818Updated last week
- FlashInfer: Kernel Library for LLM Serving☆3,723Updated this week
- ☆1,176Updated 2 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,856Updated 6 months ago
- ☆349Updated this week
- Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature se…☆70Updated this week
- DLRover: An Automatic Distributed Deep Learning System☆1,545Updated last week