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
+1 -5
View File
@@ -20,15 +20,11 @@ def models_list(*, all: bool = True, keywords: Optional[list[str]] = None):
("facebook/opt-125m", {}),
("nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", {
"dtype": torch.float16,
"quantization": "compressed-tensors"
}),
("neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic", {
"dtype": torch.float16,
"quantization": "compressed-tensors"
}),
("neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", {
"quantization": "compressed-tensors"
}),
("neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", {}),
("meta-llama/Llama-3.2-1B-Instruct", {}),
]