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

[V1] V1 Enablement Oracle (#13726)

Browse Source 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/lora/test_lora_functions.py
View File

@@ -8,7 +8,7 @@ import os
import pytest
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
from vllm.entrypoints.llm import LLM
from vllm.engine.llm_engine import LLMEngine
from vllm.lora.request import LoRARequest
MODEL_PATH = "meta-llama/Llama-2-7b-hf"
@@ -43,7 +43,7 @@ def test_lora_functions_sync():
gpu_memory_utilization=0.8,
enforce_eager=True)
llm = LLM.get_engine_class().from_engine_args(engine_args)
llm = LLMEngine.from_engine_args(engine_args)
def run_check(fn, args, expected: list):
fn(args)