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 17, 05:30 UTC
Avoid multiple redefinition (#1817)
Mingcan Xiang committed
Dec 14, 2023 at 12:35 UTC
614856da25fe59f633af865aefc874fad32d25a0
4 files changed
+8
csrc/cache.h
+2
@@ -1,3 +1,5 @@
1
+#pragma once
2
+
3
#include <torch/extension.h>
4
5
#include <map>
csrc/cuda_utils.h
+2
@@ -1,3 +1,5 @@
1
+#pragma once
2
+
3
#include <torch/extension.h>
4
5
int get_device_attribute(
csrc/dispatch_utils.h
+2
@@ -2,6 +2,8 @@
2
* Adapted from
3
* https://github.com/pytorch/pytorch/blob/v2.0.1/aten/src/ATen/Dispatch.h
4
*/
5
+#pragma once
6
+
7
#include <torch/extension.h>
8
9
#define VLLM_DISPATCH_CASE_FLOATING_TYPES(...) \
csrc/ops.h
+2
@@ -1,3 +1,5 @@
1
+#pragma once
2
+
3
#include <torch/extension.h>
4
5
void paged_attention_v1(