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

[XPU] Delay BF16 check to worker init for spawn compatibility (#22979)

Browse Source 
Signed-off-by: chzhang <chaojun.zhang@intel.com>
This commit is contained in:
Chaojun Zhang
2025-08-26 04:09:26 +08:00
committed by GitHub
parent 9188ae7cb5
commit 8a044754bd
6 changed files with 60 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
vllm/v1/worker/gpu_worker.py
View File

@@ -167,7 +167,7 @@ class Worker(WorkerBase):
self.device = torch.device(f"cuda:{self.local_rank}")
current_platform.set_device(self.device)
_check_if_gpu_supports_dtype(self.model_config.dtype)
current_platform.check_if_supports_dtype(self.model_config.dtype)
gc.collect()
torch.cuda.empty_cache()
@@ -612,23 +612,3 @@ def init_worker_distributed_environment(
parallel_config.pipeline_parallel_size)
ensure_kv_transfer_initialized(vllm_config)
def _check_if_gpu_supports_dtype(torch_dtype: torch.dtype):
# Check if the GPU supports the dtype.
if torch_dtype == torch.bfloat16: # noqa: SIM102
if not current_platform.has_device_capability(80):
capability = current_platform.get_device_capability()
gpu_name = current_platform.get_device_name()
if capability is None:
compute_str = "does not have a compute capability"
else:
version_str = capability.as_version_str()
compute_str = f"has compute capability {version_str}"
raise ValueError(
"Bfloat16 is only supported on GPUs with compute capability "
f"of at least 8.0. Your {gpu_name} GPU {compute_str}. "
"You can use float16 instead by explicitly setting the "
"`dtype` flag in CLI, for example: --dtype=half.")