nki(softmax): NKI (Trainium) implementation - #302
Open
bowencui123 wants to merge 2 commits into
Open
bowencui123 wants to merge 2 commits into
bowencui123 wants to merge 2 commits into
Conversation
Split out of the consolidated NKI branch cecilia/feature/nki-vector-add (nki-all-operators, PR #259) so each operator can be reviewed on its own. Supersedes PR #191 (older per-operator branch). - includes `NkiAutotuner` wiring (search space over the kernel's tile/loop parameter; defaults unchanged) Co-Authored-By: Cecilia123li <68335867+Cecilia123li@users.noreply.github.com> Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012Q38kGmXvyoeM1qtCbheSL
This was referenced Aug 29, 2026
Tunables mirror the Triton search space (`BLOCK_SIZE`/`BLOCK_N`); defaults are the previous constants, so autotune=False is unchanged. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012Q38kGmXvyoeM1qtCbheSL
zzczzc20
approved these changes
Sep 8, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
NKI (AWS Trainium) implementation of softmax, split out of the consolidated NKI branch
cecilia/feature/nki-vector-add(nki-all-operators, #259) so each operator can be reviewed independently. Supersedes #191 (older per-operator branch: legacyneuronxcc.nkiimports; this is the migratedimport nkiversion).Files: A benchmarks/operators/softmax/impl_nki.py
Status: verified on trn2 (default + autotune; NKI 0.055 ms @ 2048x512 fp16)
NkiAutotunerwiring (search space over the kernel's tile/loop parameter; defaults unchanged)Implementation by @Cecilia123li. Timing/identity infrastructure: #261; Trainium peak/roofline infra: #262.
🤖 Generated with Claude Code
https://claude.ai/code/session_012Q38kGmXvyoeM1qtCbheSL
Autotune (0ac2225)
free_cap(one-pass vs streaming switch),block_size(streamed column tile)BLOCK_SIZE/BLOCK_Nautotune=Falsekeeps the previous constants (default numbers unchanged). Validation on trn2, case 0 (default run + autotune code path with the candidate timer stubbed — no sweep;--autotuneruns a real sweep):