Amd Python Packages

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

pyopencl

OpenCL integration for Python, plus shiny features

vllm-tpu

A high-throughput and memory-efficient inference and serving engine for LLMs

dstack

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

lmcache

Supercharge Your LLM with the Fastest KV Cache Layer

conch-triton-kernels

A "standard library" of Triton kernels.

amd-gaia

Build AI agents for your PC

uccl

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

amdfan

Fan monitor and controller for AMD gpus in Linux

eyepy

A python package to read, analyse and visualize OCT and fundus data from various sources.

onnx-web

web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD

eyepie

A python package to read, analyse and visualize OCT and fundus data from various sources.

nabla-ml

Nabla: High-Performance Scientific Computing

grilly

GPU-accelerated neural network operations using Vulkan compute shaders

ai-dynamo-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

jellycoder

Video encoder aiming to reduce filesize and re-encode videos to make them run on a JellyFin server. Reduction in size so we can add more videos to our servers. Re-encoding to ensure the videos do not throw a playback error.

vllm-acc

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-xft

A high-throughput and memory-efficient inference and serving engine for LLMs

lmcache-cli

Supercharge Your LLM with the Fastest KV Cache Layer

gputop

Real-time GPU monitoring tool

wxy-test

A high-throughput and memory-efficient inference and serving engine for LLMs

nextai-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-consul

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-musa

A high-throughput and memory-efficient inference and serving engine for LLMs