[StaticQuant] Update how block_size is calculated with Observers #815
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/815
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit de0b7fd with merge base 848e123 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
drisspg
force-pushed
the
drisspg/stack/10
branch
from
82265e7 to
2579f23
Compare
facebook-github-bot
added
the
CLA Signed
drisspg
force-pushed
the
drisspg/stack/10
branch
3 times, most recently
from
591472c to
155e41c
Compare
drisspg
commented
Sep 5, 2024
jerryzh168
reviewed
Sep 5, 2024
jerryzh168
approved these changes
Sep 5, 2024
drisspg
force-pushed
the
drisspg/stack/10
branch
from
155e41c to
7caa703
Compare
stack-info: PR: #815, branch: drisspg/stack/10
drisspg
force-pushed
the
drisspg/stack/10
branch
from
7caa703 to
de0b7fd
Compare
HDCharles
pushed a commit
that referenced
this pull request
Sep 9, 2024
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
…ytorch#815) By wrapping attempt to load a model with `try {} catch (std::runtime_error) {}` and attempting to create model on GPU first, as attempt to load CPU model on CUDA destroys CUDA context (bugs/fixes againt PyTorch are coming, tracked in pytorch/pytorch#126547 ) Also, fix two bugs in the repo: - Initialize `Tokenizer::initialized_` to false - Change name of the tokenizer file in a workflow from `tokenizer.bin` to `tokenizer.model` Fixes pytorch/torchchat#709 Test plan: ``` python3 torchchat.py export --checkpoint-path checkpoints/stories15M/model.pth --output-dso-path model_cpu.so --device cpu python3 torchchat.py export --checkpoint-path checkpoints/stories15M/model.pth --output-dso-path model.so ./cmake-out/aoti_run ./model.so -z checkpoints/stories15M/tokenizer.model ./cmake-out/aoti_run ./model_cpu.so -z checkpoints/stories15M/tokenizer.model ```
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.
Stacked PRs:
[StaticQuant] Update how block_size is calculated with Observers