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

[bugfix] fix full graph tests (#10581)

Browse Source 
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
youkaichao 2024-11-22 10:02:14 -08:00 committed by GitHub
parent 11fcf0e066
commit db100c5cde
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/compile/utils.py
View File

@ -4,7 +4,7 @@ import torch
from tests.quantization.utils import is_quant_method_supported
from vllm import LLM, SamplingParams
from vllm.config import CompilationConfig, CompilationLevel
from vllm.config import CompilationLevel
from vllm.platforms import current_platform
TEST_MODELS = [
@ -85,7 +85,7 @@ def check_full_graph_support(model,
enforce_eager=True,
tensor_parallel_size=tp_size,
disable_custom_all_reduce=True,
compilation_config=CompilationConfig(level=optimization_level),
compilation_config=optimization_level,
**model_kwargs)
outputs = llm.generate(prompts, sampling_params)