[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)
Signed-off-by: Chengyi Nie <cnie@roblox.com> Co-authored-by: Chengyi Nie <cnie@roblox.com> Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
co-authored by
Chengyi Nie
Cursor
parent
3b6a204789
commit
fa2a33b893
@@ -48,12 +48,11 @@ WEIGHT_LOADER_V2_SUPPORTED = [
|
||||
"CompressedTensorsLinearTransformMethod",
|
||||
"AWQMarlinLinearMethod",
|
||||
"AWQLinearMethod",
|
||||
"GPTQMarlinLinearMethod",
|
||||
"AutoGPTQLinearMethod",
|
||||
"Fp8LinearMethod",
|
||||
"MarlinLinearMethod",
|
||||
"GPTQMarlin24LinearMethod",
|
||||
"TPUInt8LinearMethod",
|
||||
"GPTQLinearMethod",
|
||||
"FBGEMMFp8LinearMethod",
|
||||
"ModelOptFp8LinearMethod",
|
||||
"ModelOptFp8PcPtLinearMethod",
|
||||
|
||||
Reference in New Issue
Block a user