Commit a087cda8 authored by zhuwenwen's avatar zhuwenwen
Browse files

remove reason of unsupported

parent 2b91ac93
...@@ -123,12 +123,12 @@ _ROCM_SWA_REASON = ("Sliding window attention (SWA) is not yet supported in " ...@@ -123,12 +123,12 @@ _ROCM_SWA_REASON = ("Sliding window attention (SWA) is not yet supported in "
"please use CK flash attention by setting " "please use CK flash attention by setting "
"`VLLM_USE_TRITON_FLASH_ATTN=0`") "`VLLM_USE_TRITON_FLASH_ATTN=0`")
_ROCM_PARTIALLY_SUPPORTED_MODELS: Dict[str, str] = { _ROCM_PARTIALLY_SUPPORTED_MODELS: Dict[str, str] = {
"Qwen2ForCausalLM": # "Qwen2ForCausalLM":
_ROCM_SWA_REASON, # _ROCM_SWA_REASON,
"MistralForCausalLM": # "MistralForCausalLM":
_ROCM_SWA_REASON, # _ROCM_SWA_REASON,
"MixtralForCausalLM": # "MixtralForCausalLM":
_ROCM_SWA_REASON, # _ROCM_SWA_REASON,
"PaliGemmaForConditionalGeneration": "PaliGemmaForConditionalGeneration":
("ROCm flash attention does not yet " ("ROCm flash attention does not yet "
"fully support 32-bit precision on PaliGemma"), "fully support 32-bit precision on PaliGemma"),
......
...@@ -11,9 +11,9 @@ from .interface import Platform, PlatformEnum ...@@ -11,9 +11,9 @@ from .interface import Platform, PlatformEnum
logger = init_logger(__name__) logger = init_logger(__name__)
if os.environ.get("VLLM_WORKER_MULTIPROC_METHOD", None) in ["fork", None]: if os.environ.get("VLLM_WORKER_MULTIPROC_METHOD", None) in ["fork", None]:
logger.warning("`fork` method is not supported by ROCm. " # logger.warning("`fork` method is not supported by ROCm. "
"VLLM_WORKER_MULTIPROC_METHOD is overridden to" # "VLLM_WORKER_MULTIPROC_METHOD is overridden to"
" `spawn` instead.") # " `spawn` instead.")
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn" os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment