biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Quantization] Deprecate Long Tail of Schemes (#31688)

Browse Source 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Robert Shaw
2026-01-08 19:07:45 -05:00
committed by GitHub
parent d62cfe546d
commit 5825bbc1f7
8 changed files with 61 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
vllm/model_executor/layers/quantization/__init__.py
View File

@@ -41,6 +41,23 @@ QuantizationMethods = Literal[
]
QUANTIZATION_METHODS: list[str] = list(get_args(QuantizationMethods))
DEPRECATED_QUANTIZATION_METHODS = [
"deepspeedfp",
"tpu_int8",
"ptpc_fp8",
"fbgemm_fp8",
"fp_quant",
"bitblas",
"gptq_marlin_24",
"gptq_bitblas",
"hqq",
"experts_int8",
"ipex",
"auto-round",
"rtn",
"petit_nvfp4",
]
# The customized quantization methods which will be added to this dict.
_CUSTOMIZED_METHOD_TO_QUANT_CONFIG = {}