Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix List input bug #838

Merged
merged 1 commit into from
Jul 30, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions examples/usage/openai_batch_chat.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,13 @@
"""
Usage:
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
python openai_batch_chat.py
Note: Before running this script,
you should create the input.jsonl file with the following content:
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo-0125", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello world! List 3 NBA players and tell a story"}],"max_tokens": 300}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo-0125", "messages": [{"role": "system", "content": "You are an assistant. "},{"role": "user", "content": "Hello world! List three capital and tell a story"}],"max_tokens": 500}}
"""

import json
import os
import time
Expand Down
11 changes: 11 additions & 0 deletions examples/usage/openai_batch_complete.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,14 @@
"""
Usage:
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
python openai_batch_complete.py
Note: Before running this script,
you should create the input.jsonl file with the following content:
{"custom_id": "request-1", "method": "POST", "url": "/v1/completions", "body": {"model": "gpt-3.5-turbo-instruct", "prompt": "List 3 names of famous soccer player: ", "max_tokens": 200}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/completions", "body": {"model": "gpt-3.5-turbo-instruct", "prompt": "List 6 names of famous basketball player: ", "max_tokens": 400}}
{"custom_id": "request-3", "method": "POST", "url": "/v1/completions", "body": {"model": "gpt-3.5-turbo-instruct", "prompt": "List 6 names of famous basketball player: ", "max_tokens": 400}}
"""

import json
import os
import time
Expand Down
20 changes: 18 additions & 2 deletions examples/usage/openai_parallel_sample.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,9 @@
response = client.completions.create(
model="default",
prompt="I am a robot and I want to study like humans. Now let's tell a story. Once upon a time, there was a little",
n=1,
n=5,
temperature=0.8,
max_tokens=32,
max_tokens=320,
)
print(response)

Expand Down Expand Up @@ -68,6 +68,22 @@
print(response)


response = client.completions.create(
model="default",
prompt=[
"prompt1: I am a robot and I want to learn like humans. Now let's begin a tale. Once upon a time, there was a small",
"prompt2: As a robot, my goal is to understand human learning. Let's start a story. In a faraway land, there lived a tiny",
"prompt3: Being a robot, I aspire to study like people. Let's share a story. Long ago, there was a little",
"prompt4: I am a robot aiming to learn like humans. Let's narrate a story. Once, in a distant kingdom, there was a young",
"prompt5: As a robot, I seek to learn in human ways. Let's tell a story. Once upon a time, in a small village, there was a young",
],
n=1,
temperature=0.8,
max_tokens=320,
)
print(response)


# Text completion
response = client.completions.create(
model="default",
Expand Down
2 changes: 1 addition & 1 deletion python/sglang/srt/openai_api/adapter.py
Original file line number Diff line number Diff line change
Expand Up @@ -361,7 +361,7 @@ def v1_generate_request(all_requests):
if len(all_requests) == 1:
prompt = prompts[0]
sampling_params_list = sampling_params_list[0]
if isinstance(prompts, str) or isinstance(prompts[0], str):
if isinstance(prompt, str) or isinstance(prompt[0], str):
prompt_kwargs = {"text": prompt}
else:
prompt_kwargs = {"input_ids": prompt}
Expand Down
Loading