vllm/csrc/cuda_utils.h

#pragma once

int64_t get_device_attribute(int64_t attribute, int64_t device_id);

int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);
Avoid multiple redefinition (#1817) 2023-12-14 12:35:58 -05:00			`#pragma once`

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047) 2024-06-09 16:23:30 -04:00			`int64_t get_device_attribute(int64_t attribute, int64_t device_id);`
[Build] Avoid building too many extensions (#1624) 2023-11-23 16:31:19 -08:00
[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047) 2024-06-09 16:23:30 -04:00			`int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);`