Add vLLM e2e tests #117
Merged
Add vLLM e2e tests #117
Conversation
This file contains 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
| # Run vLLM with saved model | ||
| print("================= RUNNING vLLM =========================") | ||
| sampling_params = SamplingParams(temperature=0.80, top_p=0.95) | ||
| llm = LLM(model=self.save_dir) |
There was a problem hiding this comment.
having a test for tp>1 is also a good idea if we can
There was a problem hiding this comment.
Yah I think that'll be a follow-up test since the structure will change a bit to deal with tp>1 with the same process
I do think that's more of a vLLM test. If anything, we could extend this to publish test models which are then pulled down for all vllm tests.
kylesayrs
approved these changes
Aug 27, 2024
kylesayrs
approved these changes
Aug 27, 2024
tests/e2e/vLLM/test_vllm.py
Outdated
| llm = LLM(model=self.save_dir) | ||
| outputs = llm.generate(self.prompts, sampling_params) | ||
| print("================= vLLM GENERATION ======================") | ||
| print(outputs) |
There was a problem hiding this comment.
Logic for perplexity tests can be borrowed from
https://github.com/vllm-project/llm-compressor/blob/main/tests/llmcompressor/transformers/compression/test_quantization.py
There was a problem hiding this comment.
I would suggest running gsm8k on 200 samples
Satrat
reviewed
Aug 27, 2024
Satrat
approved these changes
Aug 28, 2024
kylesayrs
pushed a commit
that referenced
this pull request
Aug 28, 2024
* add first test * update tests * update to use config files * update test * update to add int8 tests * update * fix condition * fix typo * add w8a16 * update * update to clear session and delete dirs * conditional import for vllm * update * update num samples * add more test cases; add custom recipe support * update model * updat recipe modifier * Update fp8_weight_only.yaml * add more test cases * try a larger model * revert * add description; save model to hub post testing
markmc
pushed a commit
to markmc/llm-compressor
that referenced
this pull request
Nov 13, 2024
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
Testing
llm-compressor-testing: https://github.com/neuralmagic/llm-compressor-testing/actions/runs/10568408144/workflow