-
-
Notifications
You must be signed in to change notification settings - Fork 11.1k
Closed
Labels
bugSomething isn't workingSomething isn't working
Description
Your current environment
vllm 0.8.4
🐛 Describe the bug
from vllm import LLM
llm = LLM("meta-llama/Llama-3.2-1B-Instruct",
gpu_memory_utilization=0.3)
prompt = [{"role": "user", "content": "Are you ok?"}]
out = llm.chat(prompt)
print(out[0].prompt_token_ids[:2], llm.get_tokenizer().bos_token_id)([128000, 128000], 128000)
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't working