Jerry Zhang's picture

9 3

Jerry Zhang

jerryzh168

·

jerryzh168

AI & ML interests

None yet

Recent Activity

reacted to cbensimon's post with 🚀 3 days 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 7 days ago

jerryzh168/Qwen3-4B-untied-weights

published a model 7 days ago

jerryzh168/Qwen3-4B-untied-weights

View all activity

Organizations

New activity in pytorch/Phi-4-mini-instruct-int4wo-hqq 2 months ago

Model Card Feedback

#1 opened 2 months ago by

Update README.md

#2 opened 2 months ago by

New activity in pytorch/Phi-4-mini-instruct-8da4w 2 months ago

Update README.md

#5 opened 2 months ago by

Update README.md

#4 opened 2 months ago by

New activity in pytorch/torchao-my-repo 2 months ago

Update app.py

#1 opened 2 months ago by

New activity in pytorch/Phi-4-mini-instruct-8da4w 3 months ago

Update README.md

#3 opened 3 months ago by

Update README.md

#2 opened 3 months ago by

Updates to model card

#1 opened 3 months ago by

New activity in optimum/llm-perf-leaderboard 7 months ago

Add torchao int4 weight only quantization as an option

#34 opened 7 months ago by

Add torchao int4 weight only quantization as an option

#34 opened 7 months ago by

Add torchao int4 weight only quantization as an option

#34 opened 7 months ago by