fixing GPTQ #148
Open
fixing GPTQ #148
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
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
HDCharles
added a commit
that referenced
this pull request
Mar 28, 2024
Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 9ed1621201317e5f655132ba11538a67c8aa5a69 Pull Request resolved: #148
facebook-github-bot
added
the
CLA Signed
Summary: trying to fix the issue with kv_cache update by changing tracing into a tensor subclass. However it seems we have less success than the fx tracer. The fx tracer breaks due k_out[:,:, input_pos] = k_val getting traced as new_var = torch.ops.aten.index_put_(k_out, [None, None, input_pos], k_val) with new var never being accessed afterward. new_var becomes hte correct multiInput value, but then is lost. The subclass ont he other hand, tries to use the func "<slot wrapper '__setitem__' of 'torch._C.TensorBase' objects>" which seems to not want to mutate k_out and so the attempt to make it a multiTensor fails. Test Plan: sh run.sh Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
HDCharles
added a commit
that referenced
this pull request
Mar 28, 2024
Summary: trying to fix the issue with kv_cache update by changing tracing into a tensor subclass. However it seems we have less success than the fx tracer. The fx tracer breaks due k_out[:,:, input_pos] = k_val getting traced as new_var = torch.ops.aten.index_put_(k_out, [None, None, input_pos], k_val) with new var never being accessed afterward. new_var becomes hte correct multiInput value, but then is lost. The subclass ont he other hand, tries to use the func "<slot wrapper '__setitem__' of 'torch._C.TensorBase' objects>" which seems to not want to mutate k_out and so the attempt to make it a multiTensor fails. Test Plan: sh run.sh Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 9ed1621201317e5f655132ba11538a67c8aa5a69 Pull Request resolved: #148
# for free
to join this conversation on GitHub.
Already have an account?
# 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.
Stack from ghstack (oldest at bottom):
Summary:
trying to fix the issue with kv_cache update by changing tracing into a
tensor subclass. However it seems we have less success than the fx
tracer. The fx tracer breaks due
k_out[:,:, input_pos] = k_val
getting traced as
new_var = torch.ops.aten.index_put_(k_out, [None, None,
input_pos], k_val)
with new var never being accessed afterward. new_var becomes hte correct
multiInput value, but then is lost.
The subclass ont he other hand, tries to use the func "<slot wrapper 'setitem' of 'torch._C.TensorBase' objects>"
which seems to not want to mutate k_out and so the attempt to make it a
multiTensor fails.
Test Plan: sh run.sh
Reviewers:
Subscribers:
Tasks:
Tags: