Make name of compressed-tensors quant method consistent across vLLM (#17255)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-28 16:28:13 +00:00
committed by GitHub
parent f94886946e
commit b6dd32aa07
5 changed files with 10 additions and 14 deletions
+2 -2
View File
@@ -130,8 +130,8 @@ class RocmPlatform(Platform):
device_control_env_var: str = "CUDA_VISIBLE_DEVICES"
supported_quantization: list[str] = [
"awq", "gptq", "fp8", "compressed_tensors", "compressed-tensors",
"fbgemm_fp8", "gguf", "quark", "ptpc_fp8"
"awq", "gptq", "fp8", "compressed-tensors", "fbgemm_fp8", "gguf",
"quark", "ptpc_fp8"
]
@classmethod
+1 -3
View File
@@ -30,9 +30,7 @@ class TpuPlatform(Platform):
ray_device_key: str = "TPU"
device_control_env_var: str = "TPU_VISIBLE_CHIPS"
supported_quantization: list[str] = [
"tpu_int8", "compressed-tensors", "compressed_tensors"
]
supported_quantization: list[str] = ["tpu_int8", "compressed-tensors"]
additional_env_vars: list[str] = [
"TPU_CHIPS_PER_HOST_BOUNDS", "TPU_HOST_BOUNDS"