mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-21 01:52:30 +08:00
* feat(dflash): load dflash2 gguf drafts for qwen3.8-flash-next * fix(dflash): accept mrope sections and reuse the float qkv buffer * docs(dflash): scope the dequantized parts to quantized ggufs
10 lines
362 B
Python
10 lines
362 B
Python
from .config import DFlashDraftConfig, parse_config
|
|
from .gguf import iter_gguf_weights, parse_gguf_config, to_gguf
|
|
from .model import DFlash2DraftModel, DFlashRing
|
|
from .weight import iter_weights
|
|
|
|
__all__ = [
|
|
"DFlash2DraftModel", "DFlashDraftConfig", "DFlashRing", "iter_gguf_weights", "iter_weights",
|
|
"parse_config", "parse_gguf_config", "to_gguf",
|
|
]
|