Spaces:
Sleeping
Sleeping
Commit History
Use Qwen non-thinking prompt for short DSSD responses e2f59ad verified
Handle tensor outputs from Qwen decoder layers 8a7d9c3 verified
Fix transformers compatibility: pin versions and rename past_key_value to past_key_values 687049b
Florian valade commited on
Track metrics during streaming, remove redundant generation re-runs 33efa44
Florian valade commited on
Merge remote 'space/main' (try fix qwen) 432ea6e
Florian valade commited on
Fix early exit inference loop to eliminate redundant computation a781577
Florian valade commited on
try fix qwen 4794a4d
fix cache position for newer version of transformers 7848d77
Florian valade commited on
Add .gitignore and clean up repository 43e76c1
Florian valade commited on
Initial commit of standalone DSSD demo for HF Spaces 72b2f6d
Florian valade commited on