mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
5df8059037
* Attempt at automatic max batch prefill. * Taking into account number of shards. * Adding more cards. * Adding A100 + H100 * Adding a few more cards. * Logprobs cost too much. * h100 better name, and keep factor of 2 * Damn inflated sparse tflops. * Typo in h100. * Updated the flops calculation (checked with fvcore). * chunking by default. * Fix prefix caching for chat completion since we removed logprobs. * More tests. * Dropping all the prefill logprobs. * Add a flag that enables users to get logprobs back. * Repairing prompt token counting. * Fixing a few tests. * Remove some scaffolding. * Attempting to reduces the issues (workarounds for now).
23 lines
620 B
Python
23 lines
620 B
Python
# https://www.gutenberg.org/cache/epub/103/pg103.txt
|
|
from openai import OpenAI
|
|
import os
|
|
import requests
|
|
|
|
if not os.path.exists("pg103.txt"):
|
|
response = requests.get("https://www.gutenberg.org/cache/epub/103/pg103.txt")
|
|
with open("pg103.txt", "w") as f:
|
|
f.write(response.text)
|
|
|
|
|
|
length = 130000
|
|
with open("pg103.txt", "r") as f:
|
|
data = f.read()
|
|
|
|
messages = [{"role": "user", "content": data[: length * 4]}]
|
|
|
|
client = OpenAI(base_url="http://localhost:8000/v1", api_key="w")
|
|
|
|
completion = client.chat.completions.create(
|
|
model="meta-llama/Llama-3.1-8B-Instruct", messages=messages, max_tokens=2
|
|
)
|