Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/692aba85-5b10-8006-817a-d5a83b020f8e
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
====== 2.1.3 Continuous Batching & In-Flight Weight Updates ====== 長いチェイン・オブ・ソートやエージェントロールアウトでは、ロールアウト長の分散が大きいため、同期バッチだと一番遅いサンプル待ちでGPUが遊びがちです。 そこで、AReal や PipelineRL で広まった手法を取り入れて: * Continuous Batching - オーケストレータが常に多数のロールアウトリクエストを「プール」しておき、 - ひとつ終わるたび即座に新リクエストを投入 → 推論GPUの利用率を常に高く維持 * In-Flight Weight Updates - Trainer から新しい重みが届くと、推論サーバは一瞬生成を中断して重みをアップデート - その後のトークンは新しいポリシーで生成 - 1本の軌跡の中に複数世代のポリシーが混在し得る - ポリシーの古さが一定ステップ数(max_off_policy_steps)を超えた軌跡は破棄 図4(p7)では、タイムライン上で「ロールアウト開始・終了」と「ポリシー更新」が重なっているイメージが描かれています。INTELLECT_3_Technical_Report
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)