make eval script also handle performance measurement #3473
+159 −108
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
Contributor Author
| Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3473
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 8aba356 with merge base e4f74be ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
vkuzo added a commit that referenced this pull request Dec 9, 2025
Summary: 1. refactors the eval script to also handle performance measurement in vllm 2. adds a simple `vllm bench latency` script to bench in vllm The script is broken on every single recipe, we'll have to fix and enable things in future PRs, will update the performance tables afterwards. Also, add convenience flags to skip model creation, lm_eval, vllm as needed to enable running just a single model + single step. Test Plan: ``` SKIP_MODEL_CREATE=1 SKIP_LM_EVAL=1 SKIP_VLLM=0 with-proxy ./benchmarks/quantization/measure_accuracy_and_performance.sh h100 ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: e1d713e ghstack-comment-id: 3634216524 Pull-Request: #3473
meta-cla bot added the CLA Signed This was referenced Dec 9, 2025
Merged
vkuzo added the topic: for developers vkuzo added a commit that referenced this pull request Dec 10, 2025
Summary: 1. refactors the eval script to also handle performance measurement in vllm 2. adds a simple `vllm bench latency` script to bench in vllm The script is broken on every single recipe, we'll have to fix and enable things in future PRs, will update the performance tables afterwards. Also, add convenience flags to skip model creation, lm_eval, vllm as needed to enable running just a single model + single step. Test Plan: ``` SKIP_MODEL_CREATE=1 SKIP_LM_EVAL=1 SKIP_VLLM=0 with-proxy ./benchmarks/quantization/measure_accuracy_and_performance.sh h100 ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 15f7481 ghstack-comment-id: 3634216524 Pull-Request: #3473
vkuzo added a commit that referenced this pull request Dec 10, 2025
Summary: 1. refactors the eval script to also handle performance measurement in vllm 2. adds a simple `vllm bench latency` script to bench in vllm The script is broken on every single recipe, we'll have to fix and enable things in future PRs, will update the performance tables afterwards. Also, add convenience flags to skip model creation, lm_eval, vllm as needed to enable running just a single model + single step. Test Plan: ``` SKIP_MODEL_CREATE=1 SKIP_LM_EVAL=1 SKIP_VLLM=0 with-proxy ./benchmarks/quantization/measure_accuracy_and_performance.sh h100 ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 15f7481 ghstack-comment-id: 3634216524 Pull-Request: #3473
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.
Summary:
vllm
vllm bench latencyscript to bench in vllmThe script is broken on every single recipe, we'll have to fix and
enable things in future PRs, will update the performance tables
afterwards.
Also, add convenience flags to skip model creation, lm_eval, vllm as
needed to enable running just a single model + single step.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: