Popular repositories Loading

1. aiconfigurator aiconfigurator Public

   Forked from ai-dynamo/aiconfigurator

   Offline optimization of your disaggregated Dynamo graph

   Python

2. gpt-oss gpt-oss Public

   Forked from openai/gpt-oss

   gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

   Python

3. TensorRT-LLM TensorRT-LLM Public

   Forked from NVIDIA/TensorRT-LLM

   TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

   C++

4. SpecForge SpecForge Public

   Forked from sgl-project/SpecForge

   Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

   Python

5. TensorRT-Model-Optimizer TensorRT-Model-Optimizer Public

   Forked from NVIDIA/Model-Optimizer

   A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…

   Python

6. mamba mamba Public

   Forked from state-spaces/mamba

   Mamba SSM architecture

   Python