Files
Mukkesh Ganesh 1ba3e719c1 feat(dflash): load dflash2 gguf drafts for qwen3.8-flash-next (#914)
* 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
2026-11-17 16:53:10 -08:00

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",
]