423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 18:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] fix accelerator (#9661)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Yaowei Zheng
2025-12-25 02:11:04 +08:00
committed by GitHub
parent 6a2eafbae3
commit a754604c11
44 changed files with 396 additions and 448 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llamafactory/model/model_utils/quantization.py
View File

@@ -94,9 +94,8 @@ def configure_quantization(
quantization_config: dict[str, Any] = getattr(config, "quantization_config", None)
quant_method = quantization_config.get("quant_method", "")
if (
quant_method not in (QuantizationMethod.MXFP4 and QuantizationMethod.FP8)
and (is_deepspeed_zero3_enabled() or is_fsdp_enabled())
if quant_method not in (QuantizationMethod.MXFP4, QuantizationMethod.FP8) and (
is_deepspeed_zero3_enabled() or is_fsdp_enabled()
):
# mxfp4 will dequant the model weights
raise ValueError("DeepSpeed ZeRO-3 or FSDP is incompatible with PTQ-quantized models.")