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

[core] remove beam search from the core (#9105)

Browse Source
This commit is contained in:
youkaichao
2024-10-06 22:47:04 -07:00
committed by GitHub
parent c8f26bb636
commit 18b296fdb2
25 changed files with 98 additions and 596 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/llm_engine_example.py
View File

@ -18,9 +18,6 @@ def create_test_prompts() -> List[Tuple[str, SamplingParams]]:
temperature=0.8,
top_p=0.95,
frequency_penalty=0.1)),
("It is only with the heart that one can see rightly",
SamplingParams(n=3, best_of=3, use_beam_search=True,
temperature=0.0)),
]

18
examples/multilora_inference.py
View File

@ -43,15 +43,6 @@ def create_test_prompts(
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,
@ -60,15 +51,6 @@ def create_test_prompts(
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)),
]