Add Output TPUT per GPU and Input TPUT per GPU columns to summary table - #178
Merged
Merged
Conversation
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR enhances the benchmark summary output by adding per-GPU metrics for input and output throughput alongside the existing total throughput metric. These granular metrics provide better visibility into individual GPU performance characteristics.
Key Changes:
- Added
input_tput_per_gpucalculation in result processing - Extended summary table to display output and input throughput per GPU separately
- Improved code maintainability with proper dictionary formatting
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
Copilot
AI
changed the title
[WIP] Add output and input TPUT per GPU to summary
Add Output TPUT per GPU and Input TPUT per GPU columns to summary table
Nov 6, 2025
Contributor
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
Contributor
📊 Line Count ReportFile: Total Lines: 956 Base Lines: 956 Change: No change ➡️ |
Oseltamivir
added a commit
that referenced
this pull request
Aug 5, 2026
…lamp Fixes the defect instead of stepping around it. b368eae clamped the low-latency ladder to 128 so the corrupt 256 rung was not measured; the corruption itself was still in the kernels we publish numbers from, at roughly 1.5-3.3% per invocation on every Blackwell SKU. The fix was already upstream. DeepEP PR #642 adds a CTA-scope fence.proxy.async.shared::cta before mbarrier_arrive(empty_barriers[stage_idx]) in LOW_LATENCY_COMBINE_RECV, so the combine consumer's shared-memory reads retire before the stage is declared empty and the producer's next TMA load refills it -- signalling empty too early is what let one output row be assembled from two tiles, which matches the observed signature exactly (norm preserved to 4 s.f., 16-40% of elements wrong). It closed #621, the same race found independently on NVL72. COLLX_DEEPEP_V2_COMMIT was fa8a9b16, the head of the pre-merge PR #605 branch, cut before #642 landed. Its one unique commit was the #630 single-node V2 init fix, which main carries as 56169594e, so moving to main loses nothing and also picks up #715 (system-scope release before the GIN barrier when scale-up spans NVLink and RDMA), #688 (NCCL Device API: runtime version for ncclDevCommCreate), #178 (SM90), #641, and #640/#627 upstream's own libnccl and SO-name handling. Verified before bumping that main still exposes every API this adapter calls: legacy Buffer kwargs incl. allow_mnnvl, get_low_latency_rdma_size_hint, low_latency_dispatch/combine, ElasticBuffer's full kwarg set, topk_idx_t, and the fp8 cast helpers. rewrite_deepep_v2 now succeeds when the source already matches, because main contains #640 and the old count(old) == 1 assertion would have aborted every leg at repository-stage. Verified against all four source states: old form rewrites, fixed form is a no-op, absent and duplicated forms still fail. _LL_LADDER_CAP returns to 256. The two constants stay separate: the receive must not be sized from max(ladder), or clamping the ladder would change the footprint that drives transport traffic and fp8 dequant volume. The cap test now asserts ladder <= buffer -- strict inequality encoded the workaround, not an invariant. The backend cache key includes the pin, so this forces a rebuild rather than reusing the old build.
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
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.
The GitHub Actions summary table only displayed total throughput per GPU. This adds separate columns for input (prefill) and output (decode) throughput to better understand performance characteristics.
Changes
utils/summarize.py
output_tput_per_gpuandinput_tput_per_gpufrom aggregated resultsutils/process_result.py
Example Output
View original Slack conversation
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.