Step-3.5-Flash-MXFP4

# Reinstall vLLM
pip uninstall vllm -y
git clone https://github.com/vllm-project/vllm.git
cd vllm
git checkout de7dd634b969adc6e5f50cff0cc09c1be1711d01
pip install -r requirements/rocm.txt
python setup.py develop
cd ..
export QUARK_MXFP4_IMPL="triton"

...

class Step3p5ForCausalLM(nn.Module, SupportsPP, MixtureOfExperts):
    hf_to_vllm_mapper = WeightsMapper(
        orig_to_new_substr={".share_expert.": ".moe.share_expert."}
    )
    
+   packed_modules_mapping = {
+           "qkv_proj": [
+               "q_proj",
+               "k_proj",
+               "v_proj",
+           ],
+           "gate_up_proj": [
+               "gate_proj",
+               "up_proj",
+           ],
+       }
    
    def __init__(
        self,
        *,
        vllm_config: VllmConfig,
        prefix: str = "",
    ):
        super().__init__()
        ...