A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 03:00 UTC
[CI] Fix CPU tests failing on `tl.exp2` import (#43311)
Signed-off-by: haosdent <haosdent@gmail.com>
haosdent committed
May 21, 2026 at 22:28 UTC
9b9d5dbaab852a1c615fe83a7f92881d353503db
1 file changed
+1
vllm/triton_utils/importing.py
+1
@@ -101,5 +101,6 @@ class TritonLanguagePlaceholder(types.ModuleType):
101
self.int32 = None
102
self.tensor = None
103
self.exp = None
104
+ self.exp2 = None
105
self.log = None
106
self.log2 = None