Skip to content
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

Jump to bottom

fix(autogptq): do not use_triton with qwen-vl #1985

Merged
merged 9 commits into from
Apr 10, 2024
Merged

fix(autogptq): do not use_triton with qwen-vl #1985

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
a60642b
Enhance autogptq backend to support VL models
thiner Mar 19, 2024
7289cb6
update dependencies for autogptq
thiner Mar 19, 2024
55edeeb
remove redundant auto-gptq dependency
thiner Mar 19, 2024
e17e819
Convert base64 to image_url for Qwen-VL model
Mar 21, 2024
597d98e
implemented model inference for qwen-vl
Mar 26, 2024
30685a6
remove user prompt from generated answer
Mar 26, 2024
afa16d3
fixed write image error
Mar 26, 2024
d05b5de
Merge tag 'v2.12.1' into feature/autogptq-fix
Apr 10, 2024
b358e7c
fixed use_triton issue when loading Qwen-VL model
thiner Apr 10, 2024
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 backend/python/autogptq/autogptq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,6 @@ def LoadModel(self, request, context):
self.model_name = "Qwen-VL-Chat"
model = AutoModelForCausalLM.from_pretrained(model_path,
trust_remote_code=request.TrustRemoteCode,
use_triton=request.UseTriton,
device_map="auto").eval()
else:
model = AutoGPTQForCausalLM.from_quantized(model_path,
Expand Down
Loading