[Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com> Signed-off-by: Chendi.Xue <chendi.xue@intel.com> Signed-off-by: Bob Zhu <bob.zhu@intel.com> Signed-off-by: zehao-intel <zehao.huang@intel.com> Signed-off-by: Konrad Zawora <kzawora@habana.ai> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com> Co-authored-by: Sanju C Sudhakaran <scsudhakaran@habana.ai> Co-authored-by: Michal Adamczyk <madamczyk@habana.ai> Co-authored-by: Marceli Fylcek <mfylcek@habana.ai> Co-authored-by: Himangshu Lahkar <49579433+hlahkar@users.noreply.github.com> Co-authored-by: Vivek Goel <vgoel@habana.ai> Co-authored-by: yuwenzho <yuwen.zhou@intel.com> Co-authored-by: Dominika Olszewska <dolszewska@habana.ai> Co-authored-by: barak goldberg <149692267+bgoldberg-habana@users.noreply.github.com> Co-authored-by: Michal Szutenberg <37601244+szutenberg@users.noreply.github.com> Co-authored-by: Jan Kaniecki <jkaniecki@habana.ai> Co-authored-by: Agata Dobrzyniewicz <160237065+adobrzyniewicz-habana@users.noreply.github.com> Co-authored-by: Krzysztof Wisniewski <kwisniewski@habana.ai> Co-authored-by: Dudi Lester <160421192+dudilester@users.noreply.github.com> Co-authored-by: Ilia Taraban <tarabanil@gmail.com> Co-authored-by: Chendi.Xue <chendi.xue@intel.com> Co-authored-by: Michał Kuligowski <mkuligowski@habana.ai> Co-authored-by: Jakub Maksymczuk <jmaksymczuk@habana.ai> Co-authored-by: Tomasz Zielinski <85164140+tzielinski-habana@users.noreply.github.com> Co-authored-by: Sun Choi <schoi@habana.ai> Co-authored-by: Iryna Boiko <iboiko@habana.ai> Co-authored-by: Bob Zhu <41610754+czhu15@users.noreply.github.com> Co-authored-by: hlin99 <73271530+hlin99@users.noreply.github.com> Co-authored-by: Zehao Huang <zehao.huang@intel.com> Co-authored-by: Andrzej Kotłowski <Andrzej.Kotlowski@intel.com> Co-authored-by: Yan Tomsinsky <73292515+Yantom1@users.noreply.github.com> Co-authored-by: Nir David <ndavid@habana.ai> Co-authored-by: Yu-Zhou <yu.zhou@intel.com> Co-authored-by: Ruheena Suhani Shaik <rsshaik@habana.ai> Co-authored-by: Karol Damaszke <kdamaszke@habana.ai> Co-authored-by: Marcin Swiniarski <mswiniarski@habana.ai> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: Jacek Czaja <jacek.czaja@intel.com> Co-authored-by: Jacek Czaja <jczaja@habana.ai> Co-authored-by: Yuan <yuan.zhou@outlook.com>
This commit is contained in:
co-authored by
Kunshang Ji
Sanju C Sudhakaran
Michal Adamczyk
Marceli Fylcek
Himangshu Lahkar
Vivek Goel
yuwenzho
Dominika Olszewska
barak goldberg
Michal Szutenberg
Jan Kaniecki
Agata Dobrzyniewicz
Krzysztof Wisniewski
Dudi Lester
Ilia Taraban
Chendi.Xue
Michał Kuligowski
Jakub Maksymczuk
Tomasz Zielinski
Sun Choi
Iryna Boiko
Bob Zhu
hlin99
Zehao Huang
Andrzej Kotłowski
Yan Tomsinsky
Nir David
Yu-Zhou
Ruheena Suhani Shaik
Karol Damaszke
Marcin Swiniarski
Woosuk Kwon
Jacek Czaja
Jacek Czaja
Yuan
parent
a5fda50a10
commit
a02a50e6e5
@@ -17,6 +17,7 @@ from vllm.config import (CacheConfig, ConfigFormat, DecodingConfig,
|
||||
from vllm.executor.executor_base import ExecutorBase
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.transformers_utils.config import (
|
||||
maybe_register_config_serialize_by_value)
|
||||
from vllm.transformers_utils.utils import check_gguf_file
|
||||
@@ -37,6 +38,7 @@ DEVICE_OPTIONS = [
|
||||
"openvino",
|
||||
"tpu",
|
||||
"xpu",
|
||||
"hpu",
|
||||
]
|
||||
|
||||
|
||||
@@ -110,7 +112,9 @@ class EngineArgs:
|
||||
pipeline_parallel_size: int = 1
|
||||
tensor_parallel_size: int = 1
|
||||
max_parallel_loading_workers: Optional[int] = None
|
||||
block_size: int = 16
|
||||
# NOTE(kzawora): default block size for Gaudi should be 128
|
||||
# smaller sizes still work, but very inefficiently
|
||||
block_size: int = 16 if not current_platform.is_hpu() else 128
|
||||
enable_prefix_caching: bool = False
|
||||
disable_sliding_window: bool = False
|
||||
use_v2_block_manager: bool = True
|
||||
@@ -397,7 +401,7 @@ class EngineArgs:
|
||||
parser.add_argument('--block-size',
|
||||
type=int,
|
||||
default=EngineArgs.block_size,
|
||||
choices=[8, 16, 32],
|
||||
choices=[8, 16, 32, 64, 128],
|
||||
help='Token block size for contiguous chunks of '
|
||||
'tokens. This is ignored on neuron devices and '
|
||||
'set to max-model-len')
|
||||
@@ -1132,8 +1136,7 @@ class EngineArgs:
|
||||
multi_step_stream_outputs=self.multi_step_stream_outputs,
|
||||
send_delta_data=(envs.VLLM_USE_RAY_SPMD_WORKER
|
||||
and parallel_config.use_ray),
|
||||
policy=self.scheduling_policy,
|
||||
)
|
||||
policy=self.scheduling_policy)
|
||||
lora_config = LoRAConfig(
|
||||
max_lora_rank=self.max_lora_rank,
|
||||
max_loras=self.max_loras,
|
||||
|
||||
Reference in New Issue
Block a user