Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions tests/models/model_test.py
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ class ModelTest(unittest.TestCase):
GROUP_SIZE = 128
DESC_ACT = False
SYM = True
V2 = False
GPTQA = False
ACT_GROUP_AWARE = True
FAIL_SAFE = True
EORA = None
Expand Down Expand Up @@ -783,7 +783,7 @@ def quantModel(self, model_id_or_path, trust_remote_code=False, dtype="auto", ne
act_group_aware=self.ACT_GROUP_AWARE,
fail_safe=self.FAIL_SAFE,
sym=self.SYM,
v2=self.V2,
gptaq=self.GPTQA,
adapter=self.EORA,
pack_impl="cpu",
vram_strategy=self.VRAM_STRATEGY,
Expand Down
2 changes: 1 addition & 1 deletion tests/models/test_act_group_aware.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ class TestHybridActOrder(ModelTest):
"acc_norm": {"value": 0.3439, "floor_pct": 0.05},
},
}
V2 = False
GPTQA = False
ACT_GROUP_AWARE = True

def test_llama3_2(self):
Expand Down
2 changes: 1 addition & 1 deletion tests/models/test_ling.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ class TestLing(ModelTest):
}
TRUST_REMOTE_CODE = True
# EVAL_BATCH_SIZE = 6
V2 = False
GPTQA = False
DEBUG = True
ACT_GROUP_AWARE = True
DESC_ACT = False
Expand Down
2 changes: 1 addition & 1 deletion tests/models/test_multi_vs_single_gpu.py
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ class TestMultiVsSingleGPU(ModelTest):
"acc_norm": {"value": 0.3549, "floor_pct": 0.05},
},
}
V2 = False
GPTQA = False
DEBUG = True
ACT_GROUP_AWARE = False
DESC_ACT = True
Expand Down
2 changes: 1 addition & 1 deletion tests/test_gptqv2.py → tests/test_gptaq.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ class TestQwen2_5_GPTQv2(ModelTest):
}
TRUST_REMOTE_CODE = False
EVAL_BATCH_SIZE = 6
V2 = True
GPTQA = True

def test_qwen2_5(self):
self.quant_lm_eval()