mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-07-25 09:20:17 +00:00
Attempt #2
This commit is contained in:
parent
0a01dde986
commit
5c3efbc763
@ -1418,7 +1418,7 @@ class FlashCausalLM(Model):
|
||||
)
|
||||
max_total_tokens = available_blocks
|
||||
else:
|
||||
max_total_tokens = batch.num_blocks
|
||||
max_total_tokens = len(batch.input_ids)
|
||||
max_input_tokens = (
|
||||
batch.num_blocks - 1
|
||||
if max_input_tokens is None
|
||||
|
Loading…
Reference in New Issue
Block a user