Skip to content

https://nvbugs/5141291: Fix convert.py script for Qwen model. #3758

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 1 commit into from
Apr 22, 2025
Merged

https://nvbugs/5141291: Fix convert.py script for Qwen model. #3758

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions tensorrt_llm/models/qwen/convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,8 @@
import torch.nn as nn
from tqdm import tqdm
from transformers import AutoConfig, AutoTokenizer
from transformers.models.qwen2.modeling_qwen2 import Qwen2DecoderLayer
from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLDecoderLayer
from transformers.pytorch_utils import Conv1D

from ..._utils import pad_vocab_size, str_dtype_to_torch
Expand Down Expand Up @@ -101,9 +103,9 @@ def smooth_qwen_model(model, scales, alpha, qwen_qkv_para, qwen_smoother):
@torch.no_grad()
def smooth_qwen2_model(model, scales, alpha, qwen_qkv_para, qwen_smoother):
# Smooth the activation and weights with smoother = $\diag{s}$
from transformers.models.qwen2.modeling_qwen2 import Qwen2DecoderLayer
for name, module in model.named_modules():
if not isinstance(module, Qwen2DecoderLayer):
if not isinstance(module, Qwen2DecoderLayer) and not isinstance(
module, Qwen2VLDecoderLayer):
continue
# qkv_proj
layer_name_q = name + ".self_attn.q_proj"
Expand Down
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -346,7 +346,6 @@ examples/test_qwen.py::test_llm_qwen_single_gpu_summary[qwen2_vl_7b_instruct-ena
examples/test_qwen.py::test_llm_qwen_single_gpu_summary[qwen2_vl_7b_instruct-enable_paged_kv_cache-enable_remove_input_padding-enable_weight_only-enable_fmha_fp32_acc] SKIP (https://nvbugs/5141290)
examples/test_qwen.py::test_llm_qwen_awq_single_gpu_summary[qwen2_vl_7b_instruct-nb:4] SKIP (https://nvbugs/5141290)
examples/test_qwen.py::test_llm_hf_qwen_quantization_1gpu[qwen2_vl_7b_instruct-fp8-bfloat16] SKIP (https://nvbugs/5141290)
examples/test_qwen.py::test_llm_qwen_smooth_quant_single_gpu_summary[qwen2_vl_7b_instruct-enable_ptpc-nb:4] SKIP (https://nvbugs/5141291)
examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoder] SKIP (https://nvbugs/5141400)
examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoderplus] SKIP (https://nvbugs/5141400)
unittest/_torch/auto_deploy/integration/test_lm_eval.py SKIP (https://nvbugs/5144854)
Expand Down