Groenenboomj/fixes causal #575
Open
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
vgokhale
approved these changes
May 13, 2024
Add Perf Kernels This is a combination of 2 commits. Add Perf Kernels Add Perf Kernels This is a combination of 6 commits. add perf-kernels fix formating issues fix unused variables and other bugs fix other issues remove scripts save check changes format save save try pre-commit check save
Change all block pointers to tensor pointers Block pointers are for nvidia TMAs. They are useful for regular loads as well but not well supported. Also cleaned up some code I came across along the way and updated comment at the top.
Add support for layouts commonly used by users. Add option for varlen / thd layout to specify equal context lengths for all batches. Also often used by users.
* remove on push for Integration Tests * rename * add post merge test * save * dtype params * skip bad config * fix more stuff
Increase CI timeout
Couple of FA optimizations Set SM scale multiplication to a constexpr. Minor asm improvement. Changed acc scaling to adjust for softmax division to multiplication with reciprocal. ~10% perf improvement. --------- Co-authored-by: Michael Melesse <[email protected]>
* streamk v0.1 * remove unused variable * fix format issues * add README * fix format issue * change num_sms to num_cus
* Add explicit multiply-reduce GEMM kernel * Remove `SPLIT_K` argument from kernel * Remove `GROUP_SIZE_M` argument from kernel * Remove conditional call to `tl.dot` from kernel * Remove table with performance data from README
groenenboomj
force-pushed
the
groenenboomj/fixes_causal
branch
from
fa2e4e7
to
ae4633c
Compare
micmelesse
reviewed
Aug 13, 2024
| @@ -1259,99 +1261,93 @@ def test_op_varlen_mqa_fwd(Z, HQ, HK, N_CTX, D_HEAD, causal, dtype=torch.float16 | |||
| #(1, 16, 8192, 63), | |||
There was a problem hiding this comment.
We should test seqlens that are small so 1, 2, 4, 16, 32, 64, 128, 256, etc ...
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.
Add support for causal masking false and some testing changes:
-- backwards kernel support for bf16
-- backwards benchmark