Skip to content

Fix loading of Qwen3 FP8 #43494

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
vasqu merged 2 commits into from
Jan 27, 2026
+20 −0
Merged

Fix loading of Qwen3 FP8 #43494

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
efe56ef
Fix loading of Qwen3 FP8
Jan 26, 2026
5aa60aa
Update tests/quantization/finegrained_fp8/test_fp8.py
githubnemo Jan 26, 2026
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: 4 additions & 0 deletions src/transformers/models/qwen3_moe/configuration_qwen3_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,10 @@ class Qwen3MoeConfig(PreTrainedConfig):
model_type = "qwen3_moe"
keys_to_ignore_at_inference = ["past_key_values"]

attribute_map = {
"num_experts": "num_local_experts",
}

# Default tensor parallel plan for base model `Qwen3Moe`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
Expand Down
4 changes: 4 additions & 0 deletions src/transformers/models/qwen3_omni_moe/configuration_qwen3_omni_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -720,6 +720,10 @@ class Qwen3OmniMoeTalkerTextConfig(PreTrainedConfig):
model_type = "qwen3_omni_moe_talker_text"
keys_to_ignore_at_inference = ["past_key_values"]

attribute_map = {
"num_experts": "num_local_experts",
}

# Default tensor parallel plan for base model `Qwen3OmniMoeTalkerText`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
Expand Down
12 changes: 12 additions & 0 deletions tests/quantization/finegrained_fp8/test_fp8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
from contextlib import ExitStack, contextmanager
from unittest.mock import patch

from parameterized import parameterized

from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, FineGrainedFP8Config, OPTForCausalLM
from transformers.quantizers.quantizer_finegrained_fp8 import FineGrainedFP8HfQuantizer
from transformers.testing_utils import (
Expand Down Expand Up @@ -137,6 +139,16 @@ def tearDown(self):
backend_empty_cache(torch_device)
gc.collect()

@parameterized.expand(
[
"hf-internal-testing/tiny-random-Qwen3MoeForCausalLM",
"hf-internal-testing/tiny-random-MixtralForCausalLM",
]
)
def test_moe_conversion_doesnt_raise(self, model_id):
quantization_config = FineGrainedFP8Config(weight_block_size=(32, 32))
AutoModelForCausalLM.from_pretrained(model_id, quantization_config=quantization_config)

def test_quantized_model_conversion(self):
"""
Simple test that checks if the quantized model has been converted properly
Expand Down