NickLucche/vllm-force-merge-stats
https://nicklucche.github.io/vllm-force-merge-stats/
I like ML that runs fast (and sometimes works too).
https://nicklucche.github.io/vllm-force-merge-stats/
Static web dashboard for GitHub PR review statistics
Top LLMs ranking by downloads + stats
GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.
Common recipes to run vLLM
This repo hosts code for vLLM CI & Performance Benchmark infrastructure.
My zsh config for getting up to speed in a new server/VM
High-performance Rust benchmark client for vLLM serving endpoints.
Performance benchmark & accuracy evaluation for vLLM
Implementation of toy games and classical AI solvers (+reinforcement learning cameo).
Simple Deep Learning library in Rust based on ndarray.
A framework for efficient model inference with omni-modality models
Implementation of a SegnetConvLSTM for Lane Detection, exploiting spatiotemporal relations in data to detect roadlanes
High Level library for running Habitat-Sim for Continual Learning applications.
llm-d is a Kubernetes-native high-performance distributed LLM inference framework
NVIDIA Inference Xfer Library (NIXL)
Image Segmentation using k-means, n-cuts and superpixels
A high-throughput and memory-efficient inference and serving engine for LLMs
AI Tensor Engine for ROCm
pdb++, a drop-in replacement for pdb (the Python debugger)
Release tooling for OpenShift
Development fork of https://github.com/huggingface/text-generation-inference
PyTorch implementation of the Pyramid CNN network from "A Pyramid CNN for Dense-Leaves Segmentation"