[Core] Add token_ids output type and enforce canonical names (#7843)

Signed-off-by: Jungle430 <junglece430@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
JungleandCodex authored and GitHub committed 2026-10-05 16:49:03 +08:00
1 parent 0b0d2d7009
commit 67d21b5fff
12 files changed
+471 -58

No files matched your search

+1 -1
View File
@@ -105,7 +105,7 @@ class OmniModelConfig(ModelConfig):
worker_type: Model Type, e.g., "ar" or "generation"
engine_output_type: Optional output type specification for the engine.
Used to route outputs to appropriate processors (e.g., "image",
"audio", "latents"). If None, output type is inferred.
"audio", "latent", "token_ids"). If None, output type is inferred.
stage_connector_config: Stage connector configuration dictionary.
Contains "name" (connector name), "extra" (extra connector config).
task_type: Model-defined startup task type. Each model validates its