Jerry Zhang's picture

9 3

Jerry Zhang

jerryzh168

·

jerryzh168

AI & ML interests

None yet

Recent Activity

reacted to cbensimon's post with 🚀 42 minutes ago

🚀 ZeroGPU now supports PyTorch native quantization via `torchao` While it hasn’t been battle-tested yet, `Int8WeightOnlyConfig` is already working flawlessly in our tests. Let us know if you run into any issues — and we’re excited to see what the community will build! ```python import spaces from diffusers import FluxPipeline from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_ pipeline = FluxPipeline.from_pretrained(...).to('cuda') quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s) @spaces.GPU def generate(prompt: str): return pipeline(prompt).images[0] ```

updated a model 3 days ago

jerryzh168/Qwen3-4B-untied-weights

published a model 3 days ago

jerryzh168/Qwen3-4B-untied-weights

View all activity

Organizations

jerryzh168 's datasets 1

jerryzh168/benchmarks

Updated Nov 21, 2024 • 12