Repository navigation
Declare parallelism and config_summary per node type - #160
Open
arav-agarwal2 wants to merge 1 commit into
Open
arav-agarwal2 wants to merge 1 commit into
arav-agarwal2 wants to merge 1 commit into
Conversation
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
arav-agarwal2
commented
Oct 29, 2026
| | `config_summary_notes` | Free form field from the submitter to contain information not captured by other fields that concatenate into config_summary. | | ||
| | `tps_utilization` | reported_system_tps / (max of all reported_system_tps for all runs) | | ||
|
|
||
| > [!NOTE] |
Contributor
Author
There was a problem hiding this comment.
Updating this as we speak - I'll move config_summary inside.
arav-agarwal2
commented
Oct 29, 2026
|
|
||
| The template omits the optional `c_min_override`; its declaration rules are in §5.4. | ||
|
|
||
| `disaggregated`, `expert_parallel`, `tensor_parallel`, `pipeline_parallel` and |
Contributor
Author
There was a problem hiding this comment.
I'm going to remove this section as it's just adding words to the rules without I think a good reason to.
§8.2.1's template put disaggregated, expert_parallel, tensor_parallel, pipeline_parallel, data_parallel and config_summary at the top level of system_desc.json, so a SUT declared one partitioning for every node type it has. §4.5.3 already contradicts that. The provisioned node-count declaration there is explicitly per node type — "a single count for a homogeneous system, one count per node type for a heterogeneous one" — and it "MUST be consistent with the parallelism configuration declared in system_desc.json (§8.2) — tensor_parallel, pipeline_parallel, expert_parallel, and data_parallel". A heterogeneous SUT that partitions differently on each node type cannot satisfy both: one SUT-wide TP has no way to express two. So the six fields move inside each node_types entry. config_summary goes with them, being the concatenation of the five. A homogeneous SUT has one entry and declares them once, exactly as before, which is every submission in the corpus today. config_summary_notes stays SUT-wide and is still an input to each node type's config_summary. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
arav-agarwal2
force-pushed
the
feat/parallelism-per-node-type
branch
from
October 29, 2026 14:50
8479e4d to
14b0225
Compare
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.
§8.2.1's template puts
disaggregated,expert_parallel,tensor_parallel,pipeline_parallel,data_parallelandconfig_summaryat the top level ofsystem_desc.json, so a SUT declares one partitioning for every node type ithas. This moves them inside each
node_typesentry.§4.5.3 already assumes they are per node type
The provisioned node-count declaration is explicit about it:
and then requires:
A heterogeneous SUT that partitions differently on each node type cannot satisfy
both rules as written: one SUT-wide
tensor_parallelhas no way to express twodifferent values, so the consistency requirement is unsatisfiable rather than
merely unchecked. Moving the fields is what makes §4.5.3 expressible.
config_summarymoves with them, being the concatenation of the five.config_summary_notesstays SUT-wide and remains an input to each node type'sconfig_summary; its table row says so.Compatibility
A homogeneous SUT has exactly one
node_typesentry, so it declares the sixfields once — same count, one nesting level deeper. That is every submission in
the corpus today, so nothing in flight becomes unexpressible; bundles do need
re-nesting, which the checker handles — see the companion PR
mlcommons/endpoints-submission-cli#146, which reads both placements.
Verification
only inside
node_types[0], and the remaining top-level keys afternode_typesarenode_config,batch,config_summary_notes,tps_utilization—batchdeliberately not moved.pre-commit run --files endpoints_rules.mdpasses (markdownlint MD013).adjustments around them, and the
config_summaryrow.🤖 Generated with Claude Code