Skip to content

[FIX] test_eval #2087

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 22, 2025
Merged

[FIX] test_eval #2087

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6c2758b
load_backend cannot use BACKEND.VLLM.
ZX-ModelCloud Oct 22, 2025
b71c13f
fix tokenizer is None when load by BACKEND.VLLM
ZX-ModelCloud Oct 22, 2025
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
1 change: 0 additions & 1 deletion gptqmodel/models/auto.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -419,7 +419,6 @@ def eval(
load_kwargs = {}

if llm_backend == "vllm":
load_backend = BACKEND.VLLM
disallowed_keys = {"pretrained", "tokenizer", "gptqmodel", "trust_remote_code", "backend", "model_id_or_path"}
load_kwargs = {k: v for k, v in model_args.items() if k not in disallowed_keys}

Expand Down
7 changes: 5 additions & 2 deletions gptqmodel/models/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -372,6 +372,8 @@ def from_quantized(

qcfg.calculate_bits_per_weight()

tokenizer = AutoTokenizer.from_pretrained(model_id_or_path, trust_remote_code=trust_remote_code)

if backend == BACKEND.VLLM or backend == BACKEND.SGLANG:
if backend == BACKEND.VLLM:
if qcfg.format != FORMAT.GPTQ and qcfg.format != FORMAT.GEMM:
Expand Down Expand Up @@ -409,7 +411,10 @@ def from_quantized(
model,
quantized=True,
quantize_config=qcfg,
tokenizer=tokenizer,
qlinear_kernel=None,
load_quantized_model=True,
trust_remote_code=trust_remote_code,
model_local_path=model_local_path,
)

Expand Down Expand Up @@ -784,8 +789,6 @@ def assign(mod, device_id):

model.eval()

tokenizer = AutoTokenizer.from_pretrained(model_id_or_path, trust_remote_code=trust_remote_code)

if backend == BACKEND.MLX:
import tempfile
try:
Expand Down