biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Hardware][ROCM] using current_platform.is_rocm (#9642)

Browse Source 
Signed-off-by: wangshuai09 <391746016@qq.com>
This commit is contained in:
wangshuai09
2024-10-28 12:07:00 +08:00
committed by GitHub
parent 34a9941620
commit 4e2d95e372
32 changed files with 165 additions and 151 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/utils.py
View File

@@ -26,7 +26,7 @@ from vllm.model_executor.model_loader.loader import get_model_loader
from vllm.platforms import current_platform
from vllm.transformers_utils.tokenizer import get_tokenizer
from vllm.utils import (FlexibleArgumentParser, GB_bytes,
cuda_device_count_stateless, get_open_port, is_hip)
cuda_device_count_stateless, get_open_port)
if current_platform.is_rocm():
from amdsmi import (amdsmi_get_gpu_vram_usage,
@@ -487,7 +487,7 @@ def wait_for_gpu_memory_to_clear(devices: List[int],
output: Dict[int, str] = {}
output_raw: Dict[int, float] = {}
for device in devices:
if is_hip():
if current_platform.is_rocm():
dev_handle = amdsmi_get_processor_handles()[device]
mem_info = amdsmi_get_gpu_vram_usage(dev_handle)
gb_used = mem_info["vram_used"] / 2**10