Martin Pluskal
pluskalm
Involved Projects and Packages
LangSmith helps your team debug, evaluate, and monitor your language models and
intelligent agents. It works with any LLM Application, including a native
integration with the LangChain Python and LangChain JS open source libraries.
Bindings for the Low-level Guidance (llguidance) Rust library, providing
super-fast structured outputs and constrained decoding for large language
models. It supports context-free grammars, JSON schemas and Lark-style
syntax to constrain token generation.
ModelScope is a Model-as-a-Service SDK for browsing, downloading and
running models from ModelScope Hub. This package ships the hub/library
core only: the cv, nlp, audio and related extras are not required.
The modelscope and ms commands delegate to python-modelscope-hub.
Python SDK and CLI to download, upload and manage models, datasets,
Studio spaces, skills and MCP servers on ModelScope Hub. Provides a
HubApi class and the modelscope-hub and ms-hub commands.
SGLang is a fast serving framework for large language models and
vision language models.
This is a CPU build: inference uses PyTorch's native CPU operators.
The Rust PyO3 extensions (multimodal preprocess, native gRPC) are
built. The embedded Rust server is not. CUDA kernels, sgl-kernel
and flashinfer are not.
Spandrel loads pre-trained PyTorch image models and auto-detects architecture from .pth / safetensors files.
Stable Diffusion is a latent text-to-image diffusion model. Thanks to a generous compute donation from Stability AI and support from LAION, we were able to train a Latent Diffusion Model on 512x512 images from a subset of the LAION-5B database. Similar to Google's Imagen, this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM. See this section below and the model card.
PyTorch Image Models (timm) is a collection of image models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts that aim to pull together a wide variety of SOTA models with ability to reproduce ImageNet training results.
TorchAO is a PyTorch-native library for quantization and sparsity of model weights and activations, for both training and inference. CPU-only build for the SGLang cone.
TorchAudio applies PyTorch to the audio domain with autograd-friendly transforms and C++ extensions.
PyTorch implementation of differentiable SDE solvers with GPU support and efficient backpropagation.
The torchvision package consists of popular datasets, model
architectures, and common image transformations for computer vision
on top of PyTorch. This build is CPU-only, matching Factory
python-torch (CUDA disabled).
Simple and tiny yield-based trampoline implementation for Python.
Transformers provides thousands of pretrained models to perform tasks on
different modalities such as text, vision, and audio.
These models can be applied on text, for tasks like text classification,
information extraction, question answering, summarization, translation
and text generation; on images, for tasks like image classification,
object detection and segmentation; and on audio, for tasks like speech
recognition and audio classification.
The library is designed with two strong goals in mind: be as easy and
fast to use as possible, and provide state-of-the-art models with a
unified API.
XGrammar is an open-source library for efficient, flexible, and portable
structured generation. It provides a fast engine for constrained decoding
of large language models against grammars such as JSON schemas, regular
expressions and context-free grammars.
MCP / Model Context Protocol related software written in GOlang (primarily), built to match a multi-linux approach.
Python related MCP software is only be available for recent openSUSE and SUSE Linux releases.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
FastMCP is the fast, Pythonic way to build Model Context Protocol (MCP)
servers and clients. This is the full distribution, pulling in fastmcp-slim
with the client and server integrations enabled; the importable "fastmcp"
module is provided by fastmcp-slim.
The wire types for the Model Context Protocol.
