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 9fdecf5 commit 9b3214aCopy full SHA for 9b3214a
vllm/platforms/rocm.py
@@ -200,7 +200,7 @@ class RocmPlatform(Platform):
200
"petit_nvfp4",
201
"torchao",
202
]
203
- # bitsandbytes is not supported on GPUs with warp size 64 (gfx9)
+ # bitsandbytes quantization not supported on Instinct (warp size 64 limitation)
204
if not on_gfx9():
205
supported_quantization += ["bitsandbytes"]
206
0 commit comments