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 16, 10:45 UTC
[Bugfix] Fix Machete unittests failing with `NotImplementedError` (#9218)
Lucas Wilkinson committed
Oct 10, 2024 at 13:39 UTC
18511aeda64b473314bb7727a97a220565e0af41
1 file changed
+4
csrc/quantization/machete/machete_pytorch.cu
+4
@@ -89,6 +89,10 @@ torch::Tensor prepack_B(torch::Tensor const& B,
89
TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CUDA, m) {
90
m.impl("machete_prepack_B", &prepack_B);
91
m.impl("machete_gemm", &gemm);
92
+}
93
+
94
+// use CatchAll since supported_schedules has no tensor arguments
95
+TORCH_LIBRARY_IMPL(TORCH_EXTENSION_NAME, CatchAll, m) {
96
m.impl("machete_supported_schedules", &supported_schedules);
97
}
98