vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-11 07:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

support smt and qlm4

Browse source
This commit is contained in:
djw 2025-07-25 12:48:51 +00:00
parent 712ad1fa3c
commit 48bc6185b5
9 changed files with 65 additions and 74 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/server/backend/interfaces/balance_serve.py
View file

@ -462,6 +462,8 @@ class BalanceServeInterface(BackendInterfaceBase):
profiler.create_and_start_timer("prefill")
query_add = sched_ext.QueryAdd()
input_ids = torch.tensor([[151331, 151333, 98964, 117392, 103408, 99668, 3837, 99073, 99444,
99052, 101052, 11314]], device='cuda')
query_add.query_token = input_ids[0].tolist()
query_length = input_ids[0].shape[0]
query_add.query_length = query_length