引入上下文长度无关的 decode CUDA Graph 路径 - #28
Merged
Merged
Conversation
kuma-loong
force-pushed
the
refactor/new-agents-md
branch
4 times, most recently
from
August 25, 2026 14:11
c2a3019 to
2a2782b
Compare
kuma-loong
force-pushed
the
refactor/new-agents-md
branch
from
August 26, 2026 11:27
299b754 to
e47c689
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
背景
现有 decode CUDA Graph 同时按 batch size 和 context length 建图,有限图预算需要在两个维度间分配。该变更增加实验性的上下文长度无关路径,使图预算可以集中覆盖 batch size,并保留原实现作为回退。
主要改动
兼容性与回退
验证
后续
该实现暂作为实验功能。后续将在统一硬件和匹配 workload 下,对比 context-aware 与 batch-only graph 的端到端吞吐、延迟、显存占用和算子开销,再决定默认策略与图预算分配。