sgl-project/sglang · critical · ValueError
Invalid projection layers
Error message
Invalid projection layers: {config.projection_layers} What it means
MiMo audio encoder construction switches on config.projection_layers to choose the projection head architecture; values outside the supported set fall through to this error. It indicates the config was authored for an unsupported or newer projection layout than this code supports.
Solutions
- Check the supported projection_layers values in mimo_audio.py build_audio_encoder and set config.projection_layers accordingly
- Re-download the audio tokenizer assets matching your sglang version (snapshot_download of the correct repo)
- Pin sglang and the MiMo checkpoint to a compatible release pair
Example fix
// before "projection_layers": "v3" // after "projection_layers": 2 // a value handled by build_audio_encoder
Defensive patterns
Strategy: validation
Validate before calling
from sglang.srt.models.mimo_audio import build_audio_encoder # inspect supported values # before launch, confirm config value is one handled in build_audio_encoder: # print the branch conditions or check release notes for your sglang version
Prevention
- Keep audio tokenizer assets and sglang version in lockstep
- Test-launch the audio model after upgrading either side
When it happens
Trigger: config.projection_layers is an unrecognized value (e.g. an int or string not in the handled branches) when the audio model is constructed during engine init. Typically triggered by a mismatched audio config.json for the MiMo checkpoint.
Common situations: Mixing audio tokenizer weights/config from a different MiMo release; upgrading sglang against an older audio config; hand-edited projection config.
Related errors
- adaln out_features mismatch
- AfmoeConfig must define `num_experts`.
- Attention backend ' ' is not supported by this attention…
- audio_cap must be non-negative, got
- audio_out_channels must be divisible by tp_size for…
AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28).
Data as JSON: /api/errors/959ed850093036cb.
Report an issue: GitHub.
Appendix: source
Thrown at python/sglang/srt/models/mimo_audio.py:1256
)
for i in range(self.audio_channels)
]
)
if config.projection_layers == 1:
self.projection = nn.Linear(
self.audio_input_local_dim * self.audio_group_size,
self.audio_out_hidden_size,
bias=False,
)
elif config.projection_layers == 2:
self.projection = AudioProjection(
self.audio_input_local_dim * self.audio_group_size,
self.audio_input_local_dim * self.audio_group_size * 4,
self.audio_out_hidden_size,
)
else:
raise ValueError(f"Invalid projection layers: {config.projection_layers}")
model_path = get_model().model_path
if not os.path.isdir(model_path):
from huggingface_hub import snapshot_download
model_path = snapshot_download(
model_path,
allow_patterns=["audio_tokenizer/*"],
)
audio_tokenizer_path = os.path.join(model_path, "audio_tokenizer")
dev = torch.device(f"cuda:{torch.cuda.current_device()}")
self.audio_tokenizer = self._load_mimo_audio_tokenizer(
audio_tokenizer_path, dev
)
@staticmethod
def _load_mimo_audio_tokenizer(
path: str, device: torch.deviceView on GitHub (pinned to 0132848349)