EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add feature: priority

Browse Source 
Signed-off-by: Jing Wang <jingwang96@qq.com>
This commit is contained in:
Jing Wang
2026-05-12 11:51:57 +00:00
parent d627a45881
commit b6549b6e38
11 changed files with 382 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
csrc/vnpu_offload/vnpu_daemon.cpp
View File

@@ -1,25 +1,29 @@
#include <iostream>
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <string.h>
#include <vector>
#include <atomic>
#include <fcntl.h>
#include <mutex>
#include <signal.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <unistd.h>
#include <vector>
#include "acl/acl.h"
#include "shm_manager.h"
#include "npu_helper.h"
#include "shm_manager.h"
#include "spdlog/spdlog.h"
static ShmManager *shm_manager = nullptr;
static inline double TO_GB(size_t bytes) {
return static_cast<double>(bytes) / (1024.0 * 1024.0 * 1024.0);
}
void handle_signal(int sig) {
if (shm_manager) {
shm_manager->stop_busy_loop();
@@ -49,7 +53,7 @@ size_t get_reserved_vram_size() {
reserved_vram_size = size_gb * 1024 * 1024 * 1024;
} catch (const std::exception &e) {
spdlog::warn("Failed to parse VNPU_RESERVED_VRAM_SIZE_GB: {}, using "
"default 8GB",
"default 8 GB",
e.what());
}
}
@@ -68,12 +72,13 @@ void ensure_context(unsigned long long device) {
}
void init_acl() {
int32_t deviceId=0;
int32_t deviceId = 0;
aclError ret = aclrtSetDevice(deviceId);
if (ret != ACL_ERROR_NONE) {
throw std::runtime_error("aclrtSetDevice failed with acl error code: " +
std::to_string(ret) + " " + __FILE__ + ":" + std::to_string(__LINE__));
throw std::runtime_error(
"aclrtSetDevice failed with acl error code: " + std::to_string(ret) +
" " + __FILE__ + ":" + std::to_string(__LINE__));
}
}
@@ -109,8 +114,9 @@ void alloc_physical(uint32_t device_id, aclrtDrvMemHandle &out_mem_handle,
spdlog::error("aclrtGetMemInfo failed, error_code: {}", error_code);
throw std::runtime_error("aclrtGetMemInfo failed");
} else {
spdlog::info("aclrtGetMemInfo succeeded, free_mem: {}, total: {}", free_mem,
total);
spdlog::info(
"aclrtGetMemInfo succeeded, free_mem: {:.2f} GB, total: {:.2f} GB",
TO_GB(free_mem), TO_GB(total));
}
aclrtPhysicalMemProp prop = {};
@@ -129,13 +135,14 @@ void alloc_physical(uint32_t device_id, aclrtDrvMemHandle &out_mem_handle,
error_code);
throw std::runtime_error("aclrtMemGetAllocationGranularity failed");
} else {
spdlog::info("aclrtMemGetAllocationGranularity succeeded, granularity: {}",
spdlog::info("aclrtMemGetAllocationGranularity succeeded, granularity: {} bytes",
granularity);
}
size_t reserved_mem_size = get_reserved_vram_size();
if (free_mem < reserved_mem_size) {
spdlog::error("Not enough free memory to reserve: {}, free_mem: {}",
reserved_mem_size, free_mem);
spdlog::error(
"Not enough free memory to reserve: {:.2f} GB, free_mem: {:.2f} GB",
TO_GB(reserved_mem_size), TO_GB(free_mem));
throw std::runtime_error("Not enough free memory to reserve");
}
out_g_size = free_mem - reserved_mem_size;
@@ -147,8 +154,8 @@ void alloc_physical(uint32_t device_id, aclrtDrvMemHandle &out_mem_handle,
spdlog::error("aclrtMallocPhysical failed, error_code: {}", error_code);
throw std::runtime_error("aclrtMallocPhysical failed");
} else {
spdlog::info("device {} aclrtMallocPhysical succeeded, size: {}", device_id,
out_g_size);
spdlog::info("device {} aclrtMallocPhysical succeeded, size: {:.2f} GB",
device_id, TO_GB(out_g_size));
}
}