Skip to content

llmcompressor.modeling.deepseek_v3

Classes:

DeepseekV3MoECalibrate 

DeepseekV3MoECalibrate(
    config: DeepseekV3Config,
    original: DeepseekV3MoE,
    calibrate_all_experts: bool,
)

Bases: Module

Patched DeepseekV3MoE which sends all tokens to all experts for calibration

Source code in llmcompressor/modeling/deepseek_v3.py 
13
14
15
16
17
18
19
20
21
22
23
24
def __init__(
    self,
    config: DeepseekV3Config,
    original: OriginalDeepseekV3MoE,
    calibrate_all_experts: bool,
):
    super().__init__()
    self.config = config
    self.experts = original.experts
    self.gate = original.gate
    self.shared_experts = original.shared_experts
    self.calibrate_all_experts = calibrate_all_experts