[docs] [P/D] add feature guide for disaggregated-prefill #3950
Conversation
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
|
👋 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. |
github-actions
bot
added
the
documentation
wangxiaoteng888
changed the title
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a comprehensive design document for the disaggregated-prefill feature. The document is well-structured, covering the motivation, usage, implementation details, DFX analysis, and known limitations. It serves as a valuable resource for understanding the architecture and functionality of this feature. The changes are clear and I have no high or critical severity concerns to report.
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
wangxiaoteng888
force-pushed
the
add_read_me_113
branch
from
7a31b3c to
18c77c5
Compare
Signed-off-by: liziyu <liziyu16@huawei.com>
whx-sjtu
reviewed
Nov 3, 2025
|
|
||
| Under the disaggregated-prefill, a global proxy receives external requests, forwarding prefill to P nodes and decode to D nodes; the KV cache (key–value cache) is exchanged between P and D nodes via peer-to-peer (P2P) communication. | ||
|
|
||
| ### 2. Implementation Design |
Collaborator
There was a problem hiding this comment.
Need framework picture here.
Contributor
There was a problem hiding this comment.
Need framework picture here.
OK, we add framework picture for mooncake connector and mooncake layerwise connector
wangxiaoteng888
force-pushed
the
add_read_me_113
branch
from
f1b5148 to
b625801
Compare
Signed-off-by: liziyu <liziyu16@huawei.com>
wangxiaoteng888
force-pushed
the
add_read_me_113
branch
from
c58ad0c to
35bf4fb
Compare
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
wangxiaoteng888
force-pushed
the
add_read_me_113
branch
from
35bf4fb to
a141605
Compare
wangxiaoteng888
force-pushed
the
add_read_me_113
branch
from
a141605 to
dc95e58
Compare
Signed-off-by: wangxiaoteng888 <56506195+wangxiaoteng888@users.noreply.github.com>
wangxiyuan
approved these changes
Nov 10, 2025
luolun
pushed a commit
to luolun/vllm-ascend
that referenced
this pull request
Nov 19, 2025
…t#3950) ### What this PR does / why we need it? add feature guide for disaggregated-prefill ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? by ci - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: wangxiaoteng888 <56506195+wangxiaoteng888@users.noreply.github.com> Co-authored-by: liziyu <liziyu16@huawei.com> Signed-off-by: luolun <luolun1995@cmbchina.com>
hwhaokun
pushed a commit
to hwhaokun/vllm-ascend
that referenced
this pull request
Nov 19, 2025
…t#3950) ### What this PR does / why we need it? add feature guide for disaggregated-prefill ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? by ci - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: wangxiaoteng888 <56506195+wangxiaoteng888@users.noreply.github.com> Co-authored-by: liziyu <liziyu16@huawei.com> Signed-off-by: hwhaokun <haokun0405@163.com>
NSDie
pushed a commit
to NSDie/vllm-ascend
that referenced
this pull request
Nov 24, 2025
…t#3950) ### What this PR does / why we need it? add feature guide for disaggregated-prefill ### Does this PR introduce _any_ user-facing change? no ### How was this patch tested? by ci - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com> Signed-off-by: liziyu <liziyu16@huawei.com> Signed-off-by: wangxiaoteng888 <56506195+wangxiaoteng888@users.noreply.github.com> Co-authored-by: liziyu <liziyu16@huawei.com> Signed-off-by: nsdie <yeyifan@huawei.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
What this PR does / why we need it?
add feature guide for disaggregated-prefill
Does this PR introduce any user-facing change?
no
How was this patch tested?
by ci