We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 9fe767d commit 6230a5dCopy full SHA for 6230a5d
tests/models/quantization/test_bitsandbytes.py
@@ -16,10 +16,11 @@
16
17
if current_platform.is_rocm():
18
from vllm.platforms.rocm import on_gfx9
19
+
20
pytestmark = pytest.mark.skipif(
21
on_gfx9(),
22
reason="bitsandbytes quantization not supported on gfx9 (warp size 64 limitation)",
-)
23
+ )
24
25
models_4bit_to_test = [
26
("facebook/opt-125m", "quantize opt model inflight"),
0 commit comments