trevor-m/dynamo
A Datacenter Scale Distributed Inference Serving Framework
Sglang team at NVIDIA (Deep learning frameworks).
Repositories
trevor-m/DeepEP
DeepEP: an efficient expert-parallel communication library
trevor-m/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
trevor-m/reyes-renderer
A REYES-style micropolygon renderer written in C++ which implements a subset of the RenderMan specification.
trevor-m/InferenceX
Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3
trevor-m/srt-slurm
NVIDIA Inference Benchmarks provide recipes in ready-to-use templates for evaluating platform speed. Validate your platform across specific AI use cases across hardware and software combinations.
trevor-m/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
trevor-m/sgl-cookbook
Cookbook of SGLang - Recipe
trevor-m/deep-gbuffers
Implementation of "Fast Global Illumination Approximations on Deep G-Buffers" (Mara et. al, 2016) using C++, OpenGL, and GLSL
trevor-m/terrain-gen
Procedurally generates a terrain rendered with OpenGL.
trevor-m/tensorflow-bicubic-downsample
tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.
trevor-m/tensorflow-SRGAN
Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)
trevor-m/flashinfer
FlashInfer: Kernel Library for LLM Serving
trevor-m/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
trevor-m/sglang
SGLang is a fast serving framework for large language models and vision language models.
trevor-m/deep-tor-detection
Using deep learning to distinguish between Tor and nonTor traffic
trevor-m/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
trevor-m/JAX-Toolbox
JAX-Toolbox
trevor-m/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
trevor-m/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
trevor-m/tensorflow
An Open Source Machine Learning Framework for Everyone
trevor-m/iree
A retargetable MLIR-based machine learning compiler and runtime toolkit.
trevor-m/openxla-pjrt-plugin
PJRT plugin for interfacing the OpenXLA compiler to Jax, PyTorch/XLA and TensorFlow
trevor-m/gpu-pathtracer
A real-time photorealistic path tracer using OpenGL GPU Compute Shaders
trevor-m/raytracer
A multithreaded Whitted ray tracer (C++) which supports reflection, refraction, shadows, interpolated textures and normals, color and intersection shaders, as well as Monte Carlo anti-aliasing, depth-of-field, and BSSSRDFs
trevor-m/xla
A machine learning compiler for GPUs, CPUs, and ML accelerators
trevor-m/mud-server
A MUD Server (Text based online multiplayer game) that uses Lua for scripting of skills and abilities.
trevor-m/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
trevor-m/nccl
Optimized primitives for collective multi-GPU communication
trevor-m/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.