Implement BGE-M3 Sparse Embeddings in SGLang (#10869)

Co-authored-by: Christian Bahls <christian.bahls@planet-ai.de>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Christian Bahls
2025-10-22 22:46:16 +02:00
committed by GitHub
parent 5dccf69713
commit 164302c7df
6 changed files with 187 additions and 8 deletions

View File

@@ -961,7 +961,7 @@ class BatchEmbeddingOutput(BaseBatchReq):
# The finish reason
finished_reasons: List[BaseFinishReason]
# The output embedding
embeddings: List[List[float]]
embeddings: Union[List[List[float]], List[Dict[int, float]]]
# Token counts
prompt_tokens: List[int]
cached_tokens: List[int]