[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
This commit is contained in:
Woosuk Kwon
2026-05-18 19:50:02 -07:00
committed by GitHub
parent 239b5ff30c
commit 287471b994
12 changed files with 189 additions and 126 deletions
@@ -113,7 +113,7 @@ def get_quantization_config(quantization: str) -> type[QuantizationConfig]:
# lazy import to avoid triggering `torch.compile` too early
from vllm.config.quantization import _ONLINE_SHORTHANDS
from vllm.model_executor.layers.quantization.quark.quark import QuarkConfig
from vllm.model_executor.models.deepseek_v4 import DeepseekV4FP8Config
from vllm.models.deepseek_v4 import DeepseekV4FP8Config
from .auto_gptq import AutoGPTQConfig
from .awq import AWQConfig