[Feature]: Native GGUF Quantization Support for DiT (#1285)

Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-02-27 11:39:14 +08:00
1 parent b19c227fb3
commit 0b884ebc6c
23 files changed
+1104 -67

No files matched your search

+5 -6
View File
@@ -31,15 +31,14 @@ class DiffusionQuantizationConfig(ABC):
# The underlying vLLM config instance
_vllm_config: "QuantizationConfig | None" = None
@classmethod
def get_name(cls) -> str:
def get_name(self) -> str:
"""Return the quantization method name (e.g., 'fp8', 'int8').
By default, delegates to the underlying vLLM config class.
By default, delegates to the underlying vLLM config instance.
"""
if cls.quant_config_cls is not None:
return cls.quant_config_cls.get_name()
raise NotImplementedError("Subclass must set quant_config_cls or override get_name()")
if self._vllm_config is not None:
return self._vllm_config.get_name()
raise NotImplementedError("Subclass must initialize _vllm_config or override get_name().")
def get_vllm_quant_config(self) -> "QuantizationConfig | None":
"""Return the underlying vLLM QuantizationConfig for linear layers."""