vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-11 15:54:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Update balance_serve.py

Browse source
This commit is contained in:
wang jiahao 2025-07-12 13:14:35 +08:00 • committed by GitHub
parent dc59af6167
commit a2e95e467a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -445,7 +445,7 @@ class BalanceServeInterface(BackendInterfaceBase):
query_add.query_length = query_length query_add.query_length = query_length
profiler.set_counter("prefill", query_length) profiler.set_counter("prefill", query_length)
#@TODO add server #@TODO add server
stop_criteria = [self.tokenizer.encode(self.tokenizer.eos_token, add_special_tokens=False),self.tokenizer.encode("<|im_end|>")] stop_criteria = [self.tokenizer.encode(self.tokenizer.eos_token, add_special_tokens=False),self.tokenizer.encode("<|im_end|>", add_special_tokens=True)]
query_add.stop_criteria = stop_criteria query_add.stop_criteria = stop_criteria
temperature, top_p, max_new_tokens = self.get_params(temperature, top_p, max_tokens, max_completion_tokens) temperature, top_p, max_new_tokens = self.get_params(temperature, top_p, max_tokens, max_completion_tokens)