-
Notifications
You must be signed in to change notification settings - Fork 558
[bugfixed] fix the bug when run the inference of quantized ds-w8a8-mtp #2134
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.
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
Conversation
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
| ) | ||
| if params_dtype is None: | ||
| params_dtype = torch.get_default_dtype() | ||
| self.params_dtype = params_dtype |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
plz add a todo here, we need to make a pr in vllm to finally fix this
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ok
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #2134 +/- ##
==========================================
+ Coverage 75.05% 76.63% +1.58%
==========================================
Files 103 107 +4
Lines 11355 11977 +622
==========================================
+ Hits 8522 9179 +657
+ Misses 2833 2798 -35
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
|
LGTM, plz update the pr message to clearly describe the bug it fixes |
vllm-project#2134) When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has no attribute 'params_dtype''. 1. add wrapper of vocab_parallel_embedding, fixed the bugs when running deepseek-w8a8-mtp Signed-off-by: curryliu <120010041@link.cuhk.edu.cn> - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
vllm-project#2134) When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has no attribute 'params_dtype''. 1. add wrapper of vocab_parallel_embedding, fixed the bugs when running deepseek-w8a8-mtp Signed-off-by: curryliu <120010041@link.cuhk.edu.cn> - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
vllm-project#2134) When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has no attribute 'params_dtype''. 1. add wrapper of vocab_parallel_embedding, fixed the bugs when running deepseek-w8a8-mtp Signed-off-by: curryliu <120010041@link.cuhk.edu.cn> - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
vllm-project#2134) When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has no attribute 'params_dtype''. 1. add wrapper of vocab_parallel_embedding, fixed the bugs when running deepseek-w8a8-mtp Signed-off-by: curryliu <120010041@link.cuhk.edu.cn> - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
When run the inference of ds-w8a8-mtp, it reported 'ParamllelLMhead has no attribute 'params_dtype''.
Signed-off-by: curryliu 120010041@link.cuhk.edu.cn