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

[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Lucas Wilkinson
2026-01-08 18:20:49 -05:00
committed by GitHub
parent 5d3b6097ad
commit 6cdf015c3c
48 changed files with 380 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/kernels/core/test_pos_encoding.py
View File

@@ -62,6 +62,7 @@ TENSORS_SHAPES_FN = [
@pytest.mark.parametrize("use_key", USE_KEY)
@torch.inference_mode()
def test_rotary_embedding(
default_vllm_config,
is_neox_style: bool,
tensor_shape_fn: Callable[[int, int, int, int], tuple[int, ...]],
batch_size: int,
@@ -123,7 +124,7 @@ def test_rotary_embedding(
@torch.inference_mode()
def test_rope_module_cache():
def test_rope_module_cache(default_vllm_config):
MAX_POSITIONS = [123, 1234]
ROPE_THETAS = [10000, 1000000]
ROPE_PARAMETERS = (