inference-optimization
/

Qwen3-32B-QKV-Cache-FP8-Per-Tensor

compressed-tensors

Model card Files Files and versions

Qwen3-32B-QKV-Cache-FP8-Per-Tensor / chat_template.jinja

Commit History

Upload folder using huggingface_hub

0bd6c83
verified

krishnateja95 commited on Dec 4, 2025