sgl-project/sglang · critical · ValueError

H3 conditioning projection expects encoder width

Error message

H3 conditioning projection expects encoder width {input_dim}, but the selected text encoder has width {int(arch.hidden_size)}

What it means

The supplied conditioning projection's input width doesn't match the selected text encoder's hidden size. The projection consumes encoder hidden states directly, so input_dim must equal arch.hidden_size.

Solutions

1. Use the projection checkpoint exported from the same encoder you're serving
2. Switch the text encoder to the one matching the projection's input width
3. Re-export the projection from the correct source model

_, in_dim, _ = MiniMaxH3ConditioningProjection.inspect(materialize_weight(resolve_weight(path)))
assert in_dim == int(arch.hidden_size), f"projection input {in_dim} != encoder {arch.hidden_size}"

When it happens

Trigger: configure_component_paths with a projection whose inspect() input_dim differs from int(arch.hidden_size).

Common situations: Using a projection exported for a different encoder width (e.g. 2048-projection with a 4096 encoder), or selecting the wrong Qwen3-VL text backbone.

Related errors

• H3 conditioning projection must output width
• H3 conditioning projection expects width
• H3 conditioning projection MLP outputs width
• adaln out_features mismatch
• H3 conditioning projection

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/ea2f5ea10807f25d. Report an issue: GitHub.

Appendix: source

Thrown at python/sglang/multimodal_gen/runtime/models/encoders/minimax_h3_qwen3vl.py:240

        source = component_paths.get("conditioning_projection")
        if source is None:
            if (
                int(arch.hidden_size) != MINIMAX_H3_QWEN3VL_HIDDEN_DIM
                or int(arch.checkpoint_num_hidden_layers)
                < MINIMAX_H3_QWEN3VL_SELECTED_LM_LAYER
            ):
                raise ValueError(
                    "MiniMax H3 Qwen3-VL encoders smaller than 32B require "
                    "--component-paths.conditioning_projection"
                )
            return

        projection_path = materialize_weight(resolve_weight(source))
        tap, input_dim, output_dim = MiniMaxH3ConditioningProjection.inspect(
            projection_path
        )
        if input_dim != int(arch.hidden_size):
            raise ValueError(
                f"H3 conditioning projection expects encoder width {input_dim}, "
                f"but the selected text encoder has width {int(arch.hidden_size)}"
            )
        if output_dim != MINIMAX_H3_QWEN3VL_HIDDEN_DIM:
            raise ValueError(
                f"H3 conditioning projection must output width "
                f"{MINIMAX_H3_QWEN3VL_HIDDEN_DIM}, got {output_dim}"
            )
        if tap <= 0 or tap > int(arch.checkpoint_num_hidden_layers):
            raise ValueError(
                f"H3 conditioning projection tap {tap} is outside the selected "
                f"encoder's {int(arch.checkpoint_num_hidden_layers)} layers"
            )
        arch.conditioning_projection_path = projection_path
        arch.num_hidden_layers = tap
        arch.text_config.num_hidden_layers = tap

    def should_materialize_checkpoint_weight(self, name: str) -> bool:

View on GitHub (pinned to 0132848349)