[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
+2 -3
View File
@@ -8,8 +8,7 @@ Run `pytest tests/quantization/test_quant_lm_head_true.py --forked`.
import pytest
import torch
from vllm.model_executor.layers.quantization.gptq import GPTQLinearMethod
from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinLinearMethod
from vllm.model_executor.layers.quantization.auto_gptq import AutoGPTQLinearMethod
from vllm.model_executor.layers.vocab_parallel_embedding import (
UnquantizedEmbeddingMethod,
)
@@ -40,7 +39,7 @@ def test_lm_head(
if lm_head_quantized:
assert isinstance(
lm_head_layer.quant_method,
(GPTQLinearMethod, GPTQMarlinLinearMethod),
AutoGPTQLinearMethod,
)
else:
assert isinstance(