huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-05-15 14:42:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: adjust batch_tokenized_inputs output in mllama

Browse Source
This commit is contained in:
drbh 2024-12-13 15:51:06 +00:00
parent 2ae152a188
commit 5c7bc91a2f
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/models/mllama_causal_lm.py
View File

@ -161,7 +161,7 @@ class MllamaCausalLMBatch(VlmCausalLMBatch):
dtype: torch.dtype, dtype: torch.dtype,
device: torch.device, device: torch.device,
) -> "VlmCausalLMBatch": ) -> "VlmCausalLMBatch":
batch_tokenized_inputs, image_inputs = cls.batch_tokenized_inputs( batch_tokenized_inputs, image_inputs, _video_inputs = cls.batch_tokenized_inputs(
pb.requests, tokenizer, processor, config pb.requests, tokenizer, processor, config
) )
batch = cls.from_tokenized(pb, tokenizer, batch_tokenized_inputs, dtype, device) batch = cls.from_tokenized(pb, tokenizer, batch_tokenized_inputs, dtype, device)