biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Update deprecated Python 3.8 typing (#13971)

Browse Source
This commit is contained in:
Harry Mellor
2025-03-03 01:34:51 +00:00
committed by GitHub
parent bf33700ecd
commit cf069aa8aa
300 changed files with 2294 additions and 2347 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/offline_inference/lora_with_quantization_inference.py
View File

@@ -7,7 +7,7 @@ Requires HuggingFace credentials for access.
"""
import gc
from typing import List, Optional, Tuple
from typing import Optional
import torch
from huggingface_hub import snapshot_download
@@ -18,7 +18,7 @@ from vllm.lora.request import LoRARequest
def create_test_prompts(
lora_path: str
) -> List[Tuple[str, SamplingParams, Optional[LoRARequest]]]:
) -> list[tuple[str, SamplingParams, Optional[LoRARequest]]]:
return [
# this is an example of using quantization without LoRA
("My name is",
@@ -49,7 +49,7 @@ def create_test_prompts(
def process_requests(engine: LLMEngine,
test_prompts: List[Tuple[str, SamplingParams,
test_prompts: list[tuple[str, SamplingParams,
Optional[LoRARequest]]]):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
@@ -63,7 +63,7 @@ def process_requests(engine: LLMEngine,
lora_request=lora_request)
request_id += 1
request_outputs: List[RequestOutput] = engine.step()
request_outputs: list[RequestOutput] = engine.step()
for request_output in request_outputs:
if request_output.finished:
print("----------------------------------------------------")