[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:
Chengyi Nie
2026-05-15 08:25:52 +08:00
committed by GitHub
co-authored by Chengyi Nie Cursor
parent 3b6a204789
commit fa2a33b893
21 changed files with 170 additions and 601 deletions
+6 -14
View File
@@ -24,31 +24,23 @@ MODEL_ARG_EXPTYPES = [
# AUTOGPTQ
# compat: autogptq <=0.7.1 is_marlin_format: bool
# Model Serialized in Exllama Format.
(
"TheBloke/Llama-2-7B-Chat-GPTQ",
None,
"gptq_marlin" if current_platform.is_cuda() else "gptq",
),
("TheBloke/Llama-2-7B-Chat-GPTQ", None, "auto_gptq"),
(
"TheBloke/Llama-2-7B-Chat-GPTQ",
"marlin",
"gptq_marlin" if current_platform.is_cuda() else "ERROR",
"auto_gptq" if current_platform.is_cuda() else "ERROR",
),
("TheBloke/Llama-2-7B-Chat-GPTQ", "gptq", "gptq"),
("TheBloke/Llama-2-7B-Chat-GPTQ", "gptq", "auto_gptq"),
("TheBloke/Llama-2-7B-Chat-GPTQ", "awq", "ERROR"),
# compat: autogptq >=0.8.0 use checkpoint_format: str
# Model Serialized in Exllama Format.
(
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
None,
"gptq_marlin" if current_platform.is_cuda() else "gptq",
),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", None, "auto_gptq"),
(
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
"marlin",
"gptq_marlin" if current_platform.is_cuda() else "ERROR",
"auto_gptq" if current_platform.is_cuda() else "ERROR",
),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "gptq", "gptq"),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "gptq", "auto_gptq"),
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", "awq", "ERROR"),
# AUTOAWQ
(