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 15, 02:15 UTC
[Bugfix] Add missing field to TritonLanguagePlaceholder (#20812)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Jul 11, 2025 at 20:25 UTC
66177189c5c93dd0d2f0670b60e6cc0cd33d0932
1 file changed
+1
vllm/triton_utils/importing.py
+1
@@ -92,3 +92,4 @@ class TritonLanguagePlaceholder(types.ModuleType):
92
self.constexpr = None
93
self.dtype = None
94
self.int64 = None
95
+ self.int32 = None