[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
+19
-3
@@ -466,9 +466,10 @@ class ModelConfig:
|
||||
|
||||
# Reminder: Please update docs/source/serving/compatibility_matrix.rst
|
||||
# If the feature combo become valid
|
||||
if device_config.device_type not in ("cuda", "tpu", "xpu"):
|
||||
if device_config.device_type not in ("cuda", "tpu", "xpu", "hpu"):
|
||||
logger.warning(
|
||||
"Async output processing is only supported for CUDA, TPU, XPU. "
|
||||
"Async output processing is only supported for CUDA, TPU, XPU "
|
||||
"and HPU."
|
||||
"Disabling it for other platforms.")
|
||||
self.use_async_output_proc = False
|
||||
return
|
||||
@@ -860,7 +861,6 @@ class LoadConfig:
|
||||
ignore_patterns: The list of patterns to ignore when loading the model.
|
||||
Default to "original/**/*" to avoid repeated loading of llama's
|
||||
checkpoints.
|
||||
|
||||
"""
|
||||
|
||||
load_format: Union[str, LoadFormat, "BaseModelLoader"] = LoadFormat.AUTO
|
||||
@@ -964,6 +964,13 @@ class ParallelConfig:
|
||||
raise ValueError(
|
||||
"TPU backend only supports Ray for distributed inference.")
|
||||
|
||||
if current_platform.is_hpu() and self.world_size > 1:
|
||||
if self.distributed_executor_backend is None:
|
||||
self.distributed_executor_backend = "ray"
|
||||
if self.distributed_executor_backend != "ray":
|
||||
raise ValueError(
|
||||
"HPU backend only supports Ray for distributed inference.")
|
||||
|
||||
if self.distributed_executor_backend is None and self.world_size > 1:
|
||||
# We use multiprocessing by default if world_size fits on the
|
||||
# current node and we aren't in a ray placement group.
|
||||
@@ -1166,6 +1173,8 @@ class DeviceConfig:
|
||||
self.device_type = "cuda"
|
||||
elif current_platform.is_neuron():
|
||||
self.device_type = "neuron"
|
||||
elif current_platform.is_hpu():
|
||||
self.device_type = "hpu"
|
||||
elif current_platform.is_openvino():
|
||||
self.device_type = "openvino"
|
||||
elif current_platform.is_tpu():
|
||||
@@ -1745,6 +1754,13 @@ def _get_and_verify_dtype(
|
||||
torch_dtype = torch.float16
|
||||
else:
|
||||
torch_dtype = config_dtype
|
||||
|
||||
if current_platform.is_hpu() and config_dtype == torch.float16:
|
||||
logger.info(
|
||||
"For HPU, we cast models to bfloat16 instead of"
|
||||
"using float16 by default. Please specify `dtype` if you "
|
||||
"want to use float16.")
|
||||
torch_dtype = torch.bfloat16
|
||||
else:
|
||||
if dtype not in _STR_DTYPE_TO_TORCH_DTYPE:
|
||||
raise ValueError(f"Unknown dtype: {dtype}")
|
||||
|
||||
Reference in New Issue
Block a user