"""Create a list of test prompts with their sampling parameters.
2 requests for base model, 4 requests for the LoRA. We define 2
different LoRA adapters (using the same model for demo purposes).
Since we also set `max_loras=1`, the expectation is that the requests
with the second LoRA adapter will be ran after all requests with the
first adapter have finished.
"""
return[
("A robot may not injure a human being",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128),None),
("To be or not to be,",
SamplingParams(temperature=0.8,
top_k=5,
presence_penalty=0.2,
max_tokens=128),None),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\n question: Name the ICAO for lilongwe international airport [/user] [assistant]",# noqa: E501
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora",1,lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]",# noqa: E501
SamplingParams(n=3,
best_of=3,
use_beam_search=True,
temperature=0,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora",1,lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\n question: Name the ICAO for lilongwe international airport [/user] [assistant]",# noqa: E501
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora2",2,lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]",# noqa: E501
SamplingParams(n=3,
best_of=3,
use_beam_search=True,
temperature=0,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora",1,lora_path)),
]
defprocess_requests(engine:LLMEngine,
test_prompts:List[Tuple[str,SamplingParams,
Optional[LoRARequest]]]):
"""Continuously process a list of prompts and handle the outputs."""
