-
-
Notifications
You must be signed in to change notification settings - Fork 10k
Improve configs - MultiModalConfig
+ PoolerConfig
+ DecodingConfig
#16789
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
Improve configs - MultiModalConfig
+ PoolerConfig
+ DecodingConfig
#16789
Conversation
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
args = [ | ||
"--dtype=bfloat16", "--max-model-len=4096", "--enforce-eager", | ||
f'--limit-mm-per-prompt={{"audio":{len(audio_assets)}}}', | ||
"--trust-remote-code" | ||
f"--limit-mm-per-prompt='{limit_mm_per_prompt}'", "--trust-remote-code" |
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.
Separate the arguments
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
MultiModalConfig
+ PoolerConfig
+ DecodingConfig
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Yang Wang <elainewy@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
Follows #16332, #16422, #16533, #16603
Notable changes:
--limit-mm-per-prompt
moves away from the customnullable_kvs
type in preference to JSON strings (which are used for all other mapping inputs)nullable_kvs
will still work as a fallback with a warning during the transition period