FlyAIBox / dcu-in-actionLinks
国产加速卡-海光DCU实战（大模型训练、微调、推理 等）
☆44Updated 3 weeks ago
Alternatives and similar repositories for dcu-in-action
Users that are interested in dcu-in-action are comparing it to the libraries listed below
Sorting:
- llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deploy…☆86Updated last year
- Manages vllm-nccl dependency☆17Updated last year
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆22Updated 3 months ago
- 官方transformers源码解析。AI大模型时代，pytorch、transformer是新操作系统，其他都是运行在其上面的软件。☆17Updated last year
- The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of y…☆29Updated 11 months ago
- 配合 HAI Platform 使用的集成化用户界面☆53Updated 2 years ago
- A minimalist benchmarking tool designed to test the routine-generation capabilities of LLMs.☆25Updated 9 months ago
- A benchmarking tool for comparing different LLM API providers' DeepSeek model deployments.☆29Updated 5 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆175Updated this week
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆89Updated last week
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆56Updated 9 months ago
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆19Updated last week
- ☆112Updated last year
- ☆70Updated 4 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆167Updated last week
- GLM Series Edge Models☆147Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆17Updated last year
- Built on the robust XTuner backend framework, XTuner Chat GUI offers a user-friendly platform for quick and efficient local model inferen…☆13Updated last year
- AgileGen: Empowering Agile-Based Generative Software Development through Human-AI Teamwork (accepted by ACM TOSEM)☆24Updated 9 months ago
- ☆55Updated 9 months ago
- ASTChunk is a Python toolkit for code chunking using Abstract Syntax Trees (ASTs), designed to create structurally sound and meaningful c…☆72Updated 2 months ago
- Delta-CoMe can achieve near loss-less 1-bit compressin which has been accepted by NeurIPS 2024☆56Updated 9 months ago
- vLLM adapter for a TGIS-compatible gRPC server.☆38Updated this week
- vLLM Router☆39Updated last year
- Yet another coding assistant powered by LLM.☆16Updated 11 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- Byzer-retrieval is a distributed retrieval system which designed as a backend for LLM RAG (Retrieval Augmented Generation). The system su…☆49Updated 5 months ago
- 🔥Your Daily Dose of AI Research from Hugging Face 🔥 Stay updated with the latest AI breakthroughs! This bot automatically collects and…☆54Updated this week
- Deepseek-r1复现科普与资源汇总☆22Updated 5 months ago
- Omni_Infer is a suite of inference accelerators designed for the Ascend NPU platform, offering native support and an expanding feature se…☆60Updated this week