Add fused x64 guardrails and TPU v0.4 profiling notes - #4
Merged
Conversation
This removes implicit reliance on global x64 behavior by checking fused-mode requirements at runtime, updates docs to clarify TPU FP64 caveats, and adds a v0.4 profiling script for fused split-overhead analysis. Made-with: Cursor
This ensures the CPU validation workflow and smoke script explicitly run with x64 enabled so fused on-device checks satisfy the runtime guard. Made-with: Cursor
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
pipeline=\"ondevice\", accumulation=\"fused\"_fully_fused_ondevice_jit)0.4.0benchmarks/tpu_v04_profile.pyfor stage-by-stage TPU profiling of v0.3 vs v0.4 fused flowValidation notes
No CI TPU lane is configured yet.
Suggested manual checks:
python benchmarks/ondevice_accumulation_validate.pypython benchmarks/tpu_fused_bench.py(TPU)python benchmarks/tpu_fused_profile.py(TPU)python benchmarks/tpu_v04_profile.py(TPU)Notes
pipeline=\"ondevice\"jax_enable_x64=Trueto be set by the callerMade with Cursor