Ascend / pytorch
Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch
☆323Updated this week
Alternatives and similar repositories for pytorch:
Users that are interested in pytorch are comparing it to the libraries listed below
- Community maintained hardware plugin for vLLM on Ascend☆393Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆682Updated 2 months ago
- FlagScale is a large model toolkit based on open-sourced projects.☆260Updated this week
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆242Updated 3 weeks ago
- FlagGems is an operator library for large language models implemented in Triton Language.☆467Updated this week
- ☆324Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆529Updated 7 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆425Updated 6 months ago
- ☆127Updated 3 months ago
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆471Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆463Updated 2 weeks ago
- [EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a V…☆443Updated this week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆232Updated last week
- GLake: optimizing GPU memory management and IO transmission.☆451Updated last week
- ☆139Updated 11 months ago
- Best practice for training LLaMA models in Megatron-LM☆646Updated last year
- Zero Bubble Pipeline Parallelism☆379Updated 3 weeks ago
- ☆128Updated 3 weeks ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆964Updated this week
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆93Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆785Updated 6 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆257Updated 9 months ago
- Efficient and easy multi-instance LLM serving☆352Updated this week
- ☆46Updated this week
- ☆159Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆783Updated 6 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆624Updated 3 weeks ago
- A PyTorch Native LLM Training Framework☆767Updated 3 months ago
- export llama to onnx☆120Updated 3 months ago
- LLM Inference benchmark☆405Updated 8 months ago