Update vLLM precompiled wheel version and refactor various components for improved functionality and error handling. Changes include modifying the get_name method in DiffusionQuantizationConfig to use class-level attributes, enhancing metadata handling in StageEngineCoreClient, and adjusting the AsyncOmni class constructor for better parameter management. Additionally, improved error handling in omni_snapshot_download and optimized initial chunk size computation in talker2code2wav_async_chunk for dynamic load adaptation.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-03-19 05:14:34 +00:00
1 parent 4f75cccacc
commit 034d579d77
7 files changed
+61 -42

No files matched your search

+5
View File
@@ -53,6 +53,11 @@ def omni_snapshot_download(model_id: str) -> str:
)
except huggingface_hub.errors.RepositoryNotFoundError:
logger.warning("Repository not found for '%s'.", model_id)
except PermissionError:
logger.warning(
"Permission denied when downloading '%s'. Assuming the model is already cached locally.",
model_id,
)
return model_id