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

fix: change GB to GiB in logging close #14979 (#15807)

Browse Source 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
This commit is contained in:
yihong
2025-04-01 01:00:50 +08:00
committed by GitHub
parent 239b7befdd
commit 2de4118243
4 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/v1/worker/gpu_model_runner.py
View File

@@ -24,8 +24,8 @@ from vllm.multimodal.utils import group_mm_inputs_by_modality
from vllm.sampling_params import SamplingType
from vllm.sequence import IntermediateTensors
from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, DeviceMemoryProfiler,
LayerBlockType, LazyLoader, cdiv, check_use_alibi,
is_pin_memory_available)
GiB_bytes, LayerBlockType, LazyLoader, cdiv,
check_use_alibi, is_pin_memory_available)
from vllm.v1.attention.backends.flash_attn import FlashAttentionMetadata
from vllm.v1.core.encoder_cache_manager import compute_encoder_budget
from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheConfig,
@@ -1206,8 +1206,8 @@ class GPUModelRunner(LoRAModelRunnerMixin):
self.device)
time_after_load = time.perf_counter()
self.model_memory_usage = m.consumed_memory
logger.info("Model loading took %.4f GB and %.6f seconds",
self.model_memory_usage / float(2**30),
logger.info("Model loading took %.4f GiB and %.6f seconds",
self.model_memory_usage / GiB_bytes,
time_after_load - time_before_load)
def _get_prompt_logprobs_dict(