[TPU][Quantization] TPU W8A8 (#11785)
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
co-authored by
Woosuk Kwon
parent
47de8821d3
commit
56fe4c297c
@@ -19,7 +19,9 @@ class TpuPlatform(Platform):
|
||||
device_name: str = "tpu"
|
||||
device_type: str = "tpu"
|
||||
dispatch_key: str = "XLA"
|
||||
supported_quantization: list[str] = ["tpu_int8"]
|
||||
supported_quantization: list[str] = [
|
||||
"tpu_int8", "compressed-tensors", "compressed_tensors"
|
||||
]
|
||||
|
||||
@classmethod
|
||||
def get_default_attn_backend(cls, selected_backend: _Backend) -> _Backend:
|
||||
|
||||
Reference in New Issue
Block a user