docs(bench): refresh benchmarks against emlx 0.4.1 - #209
Open
ausimian wants to merge 1 commit into
Open
Conversation
Bump the emlx pin from ~> 0.3.1 to ~> 0.4.0 in both bench scripts and rerun the full five-tier suite plus the Qwen3-4B addendum. EMLX 0.4 is a major performance upgrade: its DistilBERT time roughly halved and its Qwen3 decode throughput jumped ~5x, while the EXLA and Emily lanes were flat, so the published Emily-vs-EMLX ratios were badly stale. - regenerate bench/emily_vs_exla_results.md (emlx 0.4.1, emily 1.0.0) and re-append the Qwen3-4B addendum section - rewrite bench/emily_vs_exla_report.md with the new numbers and a 'changes since 0.3.1' section - update the README EMLX comparison: 2.72x/5.82x/~3.2x becomes 1.44x (DistilBERT) / 1.26x (Qwen3-0.6B) / 1.17x (Qwen3-4B) - EMLX 0.4.1 still does not complete the ViT-base or Whisper-tiny tiers; Emily-vs-EXLA numbers are essentially unchanged - add RELEASE.md entry
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
EMLX 0.4 is a major performance upgrade over the 0.3.1 the published benchmarks were recorded against, so the README/report Emily-vs-EMLX ratios were badly stale. This reruns the full five-tier suite plus the Qwen3-4B addendum against emlx 0.4.1 and refreshes every published number.
Measured changes (M4 Pro 24 GB, same host as the June baseline)
The EXLA and Emily lanes moved only a few percent between runs, so the delta is the emlx upgrade itself. Emily native/fuse remain fastest on every tier both stacks complete, but the story is now compiler-vs-compiler: emlx 0.4 comfortably beats Emily's eager lane on decode.
Changes
~> 0.4.0in both bench scriptsbench/emily_vs_exla_results.md(emlx 0.4.1 / emily 1.0.0) and re-append the Qwen3-4B addendumbench/emily_vs_exla_report.mdwith the new numbers, updated charts, and a 'changes since 0.3.1' sectionRELEASE.mdentrymix precommitgreen (737 tests, 0 failures).