[DRAFT] Try make quantize kv cache work #6926
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6926
Note: Links to docs will display an error until the docs builds have been completed. ❗ 2 Active SEVsThere are 2 currently active SEVs. If your PR is affected, please view them below:
❌ 13 New FailuresAs of commit a3daba3 with merge base b4ab76f ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jackzhxng
commented
Nov 18, 2024
Comment on lines
+145
to
+151
| # if self.use_kv_cache: | ||
| # print("Setting up KV cache on the model...") | ||
| # self.model_.setup_caches( | ||
| # batch_size=1, | ||
| # dtype=self.dtype, | ||
| # decoder_max_seq_len=self.max_seq_len, | ||
| # ) |
Contributor
Author
There was a problem hiding this comment.
Need to do this because source transform happens after the model is set up, and we need to call the new swapped-in ET attention's setup_cache function. So we move the setup_cache to after the source transform
Comment on lines
+567
to
+575
| if args.model in TORCHTUNE_DEFINED_MODELS: | ||
| if args.use_kv_cache: | ||
| print("Setting up the KV cache...") | ||
| model_manager.model.setup_caches( | ||
| batch_size=1, | ||
| dtype=dtype_override.to_torch_dtype(), | ||
| decoder_max_seq_len=args.max_seq_length, | ||
| ) | ||
| return model_manager |
Contributor
Author
There was a problem hiding this comment.
Setup_cache moved here
kimishpatel
reviewed
Nov 20, 2024
| batch_size=batch_size, | ||
| max_seq_len=max_seq_len, | ||
| num_kv_heads=self.num_kv_heads, | ||
| # self.kv_cache = InferenceKVCache( |
Contributor
There was a problem hiding this comment.
can you try adding from executorch.extension.llm.custom_ops import * here and see if that works?
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
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.