biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Inclusion of InternVLChatModel In PP_SUPPORTED_MODELS(Pipeline Parallelism) (#7860)

Browse Source
This commit is contained in:
manikandan.tm@zucisystems.com
2024-09-05 17:03:37 +05:30
committed by GitHub
parent 288a938872
commit 8685ba1a1e
6 changed files with 90 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/utils.py
View File

@@ -178,7 +178,12 @@ def compare_two_settings(model: str,
env2: The second set of environment variables to pass to the API server.
"""
tokenizer = AutoTokenizer.from_pretrained(model)
trust_remote_code = "--trust-remote-code"
if trust_remote_code in arg1 or trust_remote_code in arg2:
tokenizer = AutoTokenizer.from_pretrained(model,
trust_remote_code=True)
else:
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = "Hello, my name is"
token_ids = tokenizer(prompt)["input_ids"]