Fix bug in assigning block_q_dq when block sizes are not specified #282
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
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
Signed-off-by: Kunjan Patel <kunjanp@google.com>
Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
…ect when 'tokamax_flash' requested Signed-off-by: Kunjan Patel <kunjanp@google.com>
Signed-off-by: Kunjan Patel <kunjanp@google.com>
entrpn
reviewed
Nov 14, 2025
docs/attention_blocks_flowchart.md
Outdated
|
|
||
| ## How block sizes matter for perfomance and accuracy | ||
|
|
||
| Block sizes key to saturating HBM bandwidth and ensuring maximum possible overlap of computation on cores with HBM use and VMEM to VREG. It is highly reccomended to tune them. |
Collaborator
There was a problem hiding this comment.
nit - mispelled recommended.
entrpn
approved these changes
Nov 14, 2025
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Outdated suggestions cannot be applied.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.
Changes
block_q_dq=None if attention_kernel == "tokamax_flash" else min(q_max_block_size, query.shape[2]),when block sizes are not specified.