Skip to content
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.

Sign up for GitHub

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

Jump to bottom

MLPerf inference scripts 20240722 #136

Merged
merged 43 commits into from
Jul 22, 2024
Merged

MLPerf inference scripts 20240722 #136

merged 43 commits into from
Jul 22, 2024

Conversation

ctuning-admin
Copy link
Member

No description provided.

anandhu-eng and others added 30 commits July 15, 2024 21:42
@anandhu-eng
updated script for redhat implementation
8d36a7c
@anandhu-eng
added llama2
9ce6826
@anandhu-eng
Merge branch 'mlperf-inference' into redhat_llama2
9ccdb4a
@arjunsuresh
Merge pull request #89 from anandhu-eng/redhat_llama2
8baa3c9 
Redhat llama2 implementation
@arjunsuresh
Fixes for redhat-openshift
1fb7e85
@arjunsuresh
Fixes for redhat-openshift
2990f18
@arjunsuresh
Fix openorca dataset meta
3f30d2b
@anandhu-eng
relinked to inference repo
d5e6217
@arjunsuresh
Merge pull request #90 from anandhu-eng/redhat_llama2
6b622f8 
relinked to inference repo
@arjunsuresh
Fix run script for redhat mlperf inference
2b3ec12
@arjunsuresh
Use mlc preprocessed dataset for openorca by default
fb8d23d
@arjunsuresh
Fix api_server in app-mlperf-inference-reference
d10b636
@anandhu-eng
added support for vllm server
a9da06e
@anandhu-eng
reverted changes made for redhat api
108b596
@arjunsuresh
Merge pull request #91 from anandhu-eng/redhat_llama2
4a2a8b1 
VLLM changes
@arjunsuresh
Minor fixes
239c03a
@arjunsuresh
vllm fixes
021e7e4
@arjunsuresh
Merge pull request #117 from GATEOverflow/mlperf-inference
387ab03 
Merge from go (vllm changes)
@arjunsuresh
support num_workers in LLAMA2
7880a41
@arjunsuresh
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
e26d6ca
@arjunsuresh
Merge pull request #118 from GATEOverflow/mlperf-inference
8a8f6bb 
Merge from go
@anandhu-eng
changes for docker
c271fde
@anandhu-eng
mapped host gpus to docker
aedd72a
@anandhu-eng
ubuntu+pytorch base image upgrade for vllm
1cb8235
@anandhu-eng
Merge branch 'GATEOverflow:mlperf-inference' into redhat_llama2
91eafcd
@anandhu-eng
added all vllm server api arguments
b5082ff
@anandhu-eng
clean temp files
78c1452
@anandhu-eng
Merge branch 'redhat_llama2' of https://github.com/anandhu-eng/cm4mlops…
2910556 
… into redhat_llama2
@anandhu-eng
delete temp file
5ad3924
@arjunsuresh
Support criteo preprocessed dataset from MLC
87a8bb5
@arjunsuresh
Merge pull request #92 from anandhu-eng/redhat_llama2
ee81196 
VLLM Server Docker Support
@arjunsuresh
Merge pull request #119 from GATEOverflow/mlperf-inference
92abd99 
Merge from go
@arjunsuresh
Added --max_test_duration for test mode
2ea8d86
@arjunsuresh
Takes in all mlperf inference durations as seconds
eecc2fd
@arjunsuresh
Merge pull request #132 from GATEOverflow/mlperf-inference
2799ffb 
Improvements to mlperf inference server scenario runs
@arjunsuresh
fixed dtype for durations
6863cbc
@arjunsuresh
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
aae1aca
@arjunsuresh
Merge pull request #133 from GATEOverflow/mlperf-inference
3955da1 
Merge from go
@arjunsuresh
Docs update
b4b12ea
@arjunsuresh
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
d12b401
@arjunsuresh
QPS -> Throughput in results table
353e221
@arjunsuresh
Removed pydantic version fix for bert
98dfb2e
@arjunsuresh
Merge pull request #135 from GATEOverflow/mlperf-inference
ef2193e 
Merge from go
@ctuning-admin ctuning-admin requested a review from a team as a code owner July 22, 2024 09:44
@github-actions GitHub Actions
Copy link

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

@ctuning-admin ctuning-admin merged commit 6267522 into dev Jul 22, 2024
32 checks passed
@github-actions github-actions bot locked and limited conversation to collaborators Jul 22, 2024
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@ctuning-admin @anandhu-eng @arjunsuresh