huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 15:32:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove unused pad_token_id for filter (#35) (#64)

Browse Source 
Co-authored-by: mswiniarsk <156412439+mswiniarsk@users.noreply.github.com>
This commit is contained in:
jkaniecki 2024-02-22 11:24:09 +01:00 committed by GitHub
parent 8f590759e3
commit f7ef414e38
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/server.py
View File

@ -59,7 +59,7 @@ class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer):
{"util": len(batch.requests)}):
if batch is None:
raise ValueError(f"Batch ID {request.batch_id} not found in cache.")
filtered_batch = batch.filter(request.request_ids, self.model.tokenizer.pad_token_id)
filtered_batch = batch.filter(request.request_ids)
self.cache.set(filtered_batch)
return generate_pb2.FilterBatchResponse(batch=filtered_batch.to_pb())