[CP] Enable FlexCP for llama3 #2145
Open
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
fegin
added a commit
that referenced
this pull request
Dec 11, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: c161349 Pull-Request: #2145
This was referenced Dec 11, 2025
meta-cla
bot
added
the
CLA Signed
fegin
added a commit
that referenced
this pull request
Dec 11, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: 4bced25 Pull-Request: #2145
fegin
added a commit
that referenced
this pull request
Dec 12, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: cf1e8d6 Pull-Request: #2145
fegin
added a commit
that referenced
this pull request
Dec 12, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: 1143a55 Pull-Request: #2145
tianyu-l
reviewed
Dec 14, 2025
fegin
added a commit
that referenced
this pull request
Dec 15, 2025
Stack from [ghstack](https://github.com/ezyang/ghstack/tree/0.12.0) (oldest at bottom): * #2145 * #2144 * __->__ #2143 1. Accept one "." (meaning the current commit) case to simplify the command line. 2. Ignore the untracked files.
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 [ghstack-poisoned]
fegin
added a commit
that referenced
this pull request
Dec 15, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: 85c9bff Pull-Request: #2145
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 [ghstack-poisoned]
fegin
added a commit
that referenced
this pull request
Dec 15, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: e3cfb0c Pull-Request: #2145
fegin
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: fd039d4 Pull-Request: #2145
fegin
added a commit
that referenced
this pull request
Dec 16, 2025
Summary: Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer. Note that this PR requires pytorch/pytorch#170201 ghstack-source-id: eb4903d Pull-Request: #2145
tianyu-l
approved these changes
Dec 16, 2025
| v: torch.Tensor, | ||
| *, | ||
| block_mask: BlockMask, | ||
| score_mod: _score_mod_signature | None = None, |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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:
Continue the previous PR, this PR enable FlexAttention + CP for llama3. FlexCP will use PTRRLoadBalancer.
Note that this PR requires pytorch/pytorch#170201