Generate workload based on prefix sharing synthetic data #840
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
happyandslow
changed the title
* Script that generates workload for prefix aware routing. Included some prepared prefix workload Signed-off-by: “Gangmuk <gangmuk@gmail.com> * generate_realistic_prefix_share_workload.py in benchmakrs/generator Signed-off-by: “Gangmuk <gangmuk@gmail.com> --------- Signed-off-by: “Gangmuk <gangmuk@gmail.com> Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
happyandslow
force-pushed
the
lexu/cache-aware-workload
branch
from
4989a69 to
33e5499
Compare
happyandslow
changed the title
Jeffwan
reviewed
Mar 12, 2025
added 5 commits
March 15, 2025 18:39
Signed-off-by: Le Xu <le.xu@bytedance.com>
…on workload) Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
Signed-off-by: Le Xu <le.xu@bytedance.com>
happyandslow
added a commit
that referenced
this pull request
Mar 16, 2025
gangmuk
added a commit
to gangmuk/aibrix-gangmuk
that referenced
this pull request
Jun 21, 2025
…t#840) * Workload generation scripts for prefix aware routing (vllm-project#820) * Script that generates workload for prefix aware routing. Included some prepared prefix workload Signed-off-by: “Gangmuk <gangmuk@gmail.com> * generate_realistic_prefix_share_workload.py in benchmakrs/generator Signed-off-by: “Gangmuk <gangmuk@gmail.com> --------- Signed-off-by: “Gangmuk <gangmuk@gmail.com> Signed-off-by: Le Xu <le.xu@bytedance.com> * Generate workload based on prefix sharing synthetic data Signed-off-by: Le Xu <le.xu@bytedance.com> * update prefix sharing from distribution Signed-off-by: Le Xu <le.xu@bytedance.com> * remove adapter name Signed-off-by: Le Xu <le.xu@bytedance.com> * update user argument Signed-off-by: Le Xu <le.xu@bytedance.com> * update README Signed-off-by: Le Xu <le.xu@bytedance.com> * fix model argument Signed-off-by: Le Xu <le.xu@bytedance.com> * adding default model to client (making compatible with older generation workload) Signed-off-by: Le Xu <le.xu@bytedance.com> * fixing None statitiscs in output file Signed-off-by: Le Xu <le.xu@bytedance.com> * update readme for references Signed-off-by: Le Xu <le.xu@bytedance.com> * clean up Signed-off-by: Le Xu <le.xu@bytedance.com> --------- Signed-off-by: “Gangmuk <gangmuk@gmail.com> Signed-off-by: Le Xu <le.xu@bytedance.com> Co-authored-by: Gangmuk Lim <gangmuk@gmail.com> Co-authored-by: Le Xu <le.xu@bytedance.com>
gangmuk
pushed a commit
to gangmuk/aibrix-gangmuk
that referenced
this pull request
Jun 21, 2025
add missing image Signed-off-by: Le Xu <le.xu@bytedance.com> Co-authored-by: Le Xu <le.xu@bytedance.com>
Yaegaki1Erika
pushed a commit
to Yaegaki1Erika/aibrix
that referenced
this pull request
Jul 23, 2025
…t#840) * Workload generation scripts for prefix aware routing (vllm-project#820) * Script that generates workload for prefix aware routing. Included some prepared prefix workload Signed-off-by: “Gangmuk <gangmuk@gmail.com> * generate_realistic_prefix_share_workload.py in benchmakrs/generator Signed-off-by: “Gangmuk <gangmuk@gmail.com> --------- Signed-off-by: “Gangmuk <gangmuk@gmail.com> Signed-off-by: Le Xu <le.xu@bytedance.com> * Generate workload based on prefix sharing synthetic data Signed-off-by: Le Xu <le.xu@bytedance.com> * update prefix sharing from distribution Signed-off-by: Le Xu <le.xu@bytedance.com> * remove adapter name Signed-off-by: Le Xu <le.xu@bytedance.com> * update user argument Signed-off-by: Le Xu <le.xu@bytedance.com> * update README Signed-off-by: Le Xu <le.xu@bytedance.com> * fix model argument Signed-off-by: Le Xu <le.xu@bytedance.com> * adding default model to client (making compatible with older generation workload) Signed-off-by: Le Xu <le.xu@bytedance.com> * fixing None statitiscs in output file Signed-off-by: Le Xu <le.xu@bytedance.com> * update readme for references Signed-off-by: Le Xu <le.xu@bytedance.com> * clean up Signed-off-by: Le Xu <le.xu@bytedance.com> --------- Signed-off-by: “Gangmuk <gangmuk@gmail.com> Signed-off-by: Le Xu <le.xu@bytedance.com> Co-authored-by: Gangmuk Lim <gangmuk@gmail.com> Co-authored-by: Le Xu <le.xu@bytedance.com>
Yaegaki1Erika
pushed a commit
to Yaegaki1Erika/aibrix
that referenced
this pull request
Jul 23, 2025
add missing image Signed-off-by: Le Xu <le.xu@bytedance.com> Co-authored-by: Le Xu <le.xu@bytedance.com>
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.
Pull Request Description
This branch lets workload generator to generate workload based on prefix shared synthetic data
Related Issues
Resolves: #813