turboderp 7af6494afa Drop device tensors for head layer during conversion

2024-02-16 17:31:19 +01:00

..

standard_cal_data

Include calibration data

2023-12-08 20:20:43 +01:00

adaptivegptq.py

Support Qwen2

2024-02-15 20:50:24 +01:00

compile.py

Prevent tensors passed to save_file from sharing memory

2024-02-01 10:14:36 +01:00

measure.py

Support Qwen2

2024-02-15 20:50:24 +01:00

optimize.py

Fix converter

2023-12-28 10:11:45 +01:00

qparams.py

Support Qwen2

2024-02-15 20:50:24 +01:00

quantize.py

Drop device tensors for head layer during conversion

2024-02-16 17:31:19 +01:00

tokenize.py

Fix bug in standard cal dataset

2023-12-16 20:30:40 +01:00