| File Name ↓ | File Size ↓ | Date ↓ |
|---|---|---|
| Parent directory/ | - | - |
| __pycache__/ | - | 2025-Nov-21 12:27 |
| __init__.py | 9.3 KiB | 2025-Nov-21 12:27 |
| accelerate.py | 7.2 KiB | 2025-Nov-21 12:27 |
| aqlm.py | 4.4 KiB | 2025-Nov-21 12:27 |
| awq.py | 20.1 KiB | 2025-Nov-21 12:27 |
| bitnet.py | 15.3 KiB | 2025-Nov-21 12:27 |
| bitsandbytes.py | 23.3 KiB | 2025-Nov-21 12:27 |
| deepspeed.py | 21.4 KiB | 2025-Nov-21 12:27 |
| eager_paged.py | 3.0 KiB | 2025-Nov-21 12:27 |
| eetq.py | 5.2 KiB | 2025-Nov-21 12:27 |
| executorch.py | 51.1 KiB | 2025-Nov-21 12:27 |
| fbgemm_fp8.py | 12.1 KiB | 2025-Nov-21 12:27 |
| finegrained_fp8.py | 14.8 KiB | 2025-Nov-21 12:27 |
| flash_attention.py | 3.1 KiB | 2025-Nov-21 12:27 |
| flash_paged.py | 4.1 KiB | 2025-Nov-21 12:27 |
| flex_attention.py | 13.4 KiB | 2025-Nov-21 12:27 |
| fp_quant.py | 1.8 KiB | 2025-Nov-21 12:27 |
| fsdp.py | 1.5 KiB | 2025-Nov-21 12:27 |
| ggml.py | 29.6 KiB | 2025-Nov-21 12:27 |
| higgs.py | 30.8 KiB | 2025-Nov-21 12:27 |
| hqq.py | 5.0 KiB | 2025-Nov-21 12:27 |
| hub_kernels.py | 8.1 KiB | 2025-Nov-21 12:27 |
| integration_utils.py | 110.4 KiB | 2025-Nov-21 12:27 |
| mistral.py | 3.9 KiB | 2025-Nov-21 12:27 |
| mxfp4.py | 18.0 KiB | 2025-Nov-21 12:27 |
| npu_flash_attention.py | 4.1 KiB | 2025-Nov-21 12:27 |
| peft.py | 28.3 KiB | 2025-Nov-21 12:27 |
| quanto.py | 4.3 KiB | 2025-Nov-21 12:27 |
| sdpa_attention.py | 5.0 KiB | 2025-Nov-21 12:27 |
| sdpa_paged.py | 2.1 KiB | 2025-Nov-21 12:27 |
| spqr.py | 5.4 KiB | 2025-Nov-21 12:27 |
| tensor_parallel.py | 48.3 KiB | 2025-Nov-21 12:27 |
| tiktoken.py | 1.6 KiB | 2025-Nov-21 12:27 |
| tpu.py | 1.4 KiB | 2025-Nov-21 12:27 |
| vptq.py | 4.4 KiB | 2025-Nov-21 12:27 |