# pytorch

このトピックのトレンドリポジトリ(9件)

AUTOMATIC1111/stable-diffusion-webui

AUTOMATIC1111/stable-diffusion-webuiOtherPython
162.8k

Stable Diffusion web UI

aiai-artdeep-learningdiffusiongradioimage-generationimage2imageimg2imgpytorchstable-diffusiontext2imagetorchtxt2imgunstableupscalingweb

rasbt/LLMs-from-scratch

rasbt/LLMs-from-scratchOtherJupyter Notebook
94.2k3回登場

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

aiartificial-intelligencechatbotchatgptdeep-learningfrom-scratchgenerative-aigptlanguage-modellarge-language-modelsllmmachine-learningneural-networkspythonpytorchtransformers

roboflow/supervision

roboflow/supervisionOtherPython
45.7k5回登場

We write your reusable computer vision tools. 💜

classificationcococomputer-visiondeep-learninghacktoberfestimage-processinginstance-segmentationlow-codemachine-learningmetricsobject-detectionoriented-bounding-boxpascal-vocpythonpytorchtensorflowtrackingvideo-processingyolo

OpenBMB/VoxCPM

OpenBMB/VoxCPMOtherPython
30.0k7回登場

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

audiodeeplearningminicpmmultilingualpythonpytorchspeechspeech-synthesistext-to-speechttstts-modelvoice-cloningvoice-designvoxcpm

microsoft/onnxruntime

microsoft/onnxruntimeOtherC++
20.3k

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

ai-frameworkdeep-learninghardware-accelerationmachine-learningneural-networksonnxpytorchscikit-learntensorflow

LMCache/LMCache

LMCache/LMCacheOtherPython
8.7k2回登場

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

amdcudafastinferencekv-cachellmpytorchrocmspeedvllm

NVlabs/Sana

NVlabs/SanaOtherPython
6.3k

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

diffusionditlinear-transformernvfp4pytorchreinforcement-learningsanasystem-algorithm-deisgntext-to-image-generationtext-to-videotransformersvideo-generation

テキスト・画像・音声・動画をまるごと高速推論!万能AIモデルの配信基盤 — vllm-omni

vllm-project/vllm-omniAIPython
3.6k

vLLM-Omniは、テキストだけでなく画像・動画・音声など複数の種類のデータを同時に扱えるAIモデルを、高速かつ低コストで動かすためのフレームワーク(ソフトウェアの骨組み)です。もともとテキスト専用だったvLLMという人気の高速推論エンジ

audio-generationdiffusionimage-generationinferencemodel-servingmultimodalpytorchtransformervideo-generation

galilai-group/stable-worldmodel

galilai-group/stable-worldmodelOtherPython
1.5k3回登場

A platform for reproducible world model research and evaluation

deep-learningjepamodel-predictive-controlpytorchworld-model