TorchAO Quantized Qwen3 Collection TorchAO quantized Qwen3 models from PyTorch team, runnable in A100, H100 through vLLM and in mobile devices through ExecuTorch • 5 items • Updated 2 days ago
torchao-testing/opt-125m-Int8DynamicActivationIntxWeightConfig-v1-0.14.0.dev Updated 3 days ago • 1.08k