[TPU] support fp8 kv cache quantization (#19292)
Signed-off-by: Chengji Yao <chengjiyao@google.com>
This commit is contained in:
@@ -35,7 +35,9 @@ class TpuPlatform(Platform):
|
||||
device_control_env_var: str = "TPU_VISIBLE_CHIPS"
|
||||
simple_compile_backend: str = "openxla"
|
||||
|
||||
supported_quantization: list[str] = ["tpu_int8", "compressed-tensors"]
|
||||
supported_quantization: list[str] = [
|
||||
"fp8", "tpu_int8", "compressed-tensors"
|
||||
]
|
||||
|
||||
additional_env_vars: list[str] = [
|
||||
"TPU_CHIPS_PER_HOST_BOUNDS", "TPU_HOST_BOUNDS"
|
||||
|
||||
Reference in New Issue
Block a user