File Name ↓ | File Size ↓ | Date ↓ |
---|---|---|
Parent directory/ | - | - |
__init__.py | 0 B | 2024-Nov-23 12:55 |
apply_spin_quant_r1_r2.py | 7.5 KiB | 2024-Nov-23 12:55 |
attention.py | 6.8 KiB | 2024-Nov-23 12:55 |
lora.py | 5.2 KiB | 2024-Nov-23 12:55 |
pre_quantization.py | 6.6 KiB | 2024-Nov-23 12:55 |
prune_vocab.py | 4.3 KiB | 2024-Nov-23 12:55 |
quantize.py | 26.9 KiB | 2024-Nov-23 12:55 |
quantized_kv_cache.py | 8.7 KiB | 2024-Nov-23 12:55 |
rms_norm.py | 755 B | 2024-Nov-23 12:55 |
rope.py | 1.5 KiB | 2024-Nov-23 12:55 |
sdpa.py | 12.8 KiB | 2024-Nov-23 12:55 |
spin_quant.py | 2.9 KiB | 2024-Nov-23 12:55 |
test_quantized_kv_cache.py | 4.3 KiB | 2024-Nov-23 12:55 |
test_sdpa_with_quantized_kv_cache.py | 3.0 KiB | 2024-Nov-23 12:55 |
vulkan_rope.py | 1.0 KiB | 2024-Nov-23 12:55 |