Repository navigation
A catalogue row says what a model needs of the machine that runs it - #45
Merged
Merged
Conversation
size: (a parameter count) and requires: {memory, accelerator} on a model row. A
runtime that knows its machine leaves out a model served on that machine alone
that the machine cannot hold, with a sentence; a row with no figure, a machine
figure the runtime does not know, and a row served elsewhere are never left
out for it. The checker refuses a size or memory figure that does not read.
spec/hardware-fit.yaml holds the readings and decisions for both ports.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
…requires # Conflicts: # CHANGELOG.md # site-docs/index.md
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A catalogue row says what a model needs of the machine that runs it
A runtime choosing among models served on its own machine could not tell whether the machine could hold one. A row said where a model was served and what it cost, but never how big it was or how much memory it took. So a local row the machine could not load was bound, and it failed on its first call.
size:is a figure: the model's parameter count (7.6B,405B,500M,8000000000) with its provenance, orunknown.requires: {memory, accelerator}:memory:is a figure for how much memory loading and running the model as served takes (4.7 GB,9 GiB).accelerator: gpusays the model runs only on an accelerator, somemory:is the accelerator's memory. Leaving it out meansnone.pact_adapters.machine.this_machine, throughos.sysconf). It does not know an accelerator, so it decides nothing about one.ModelEntry.fits_machineandsatisfies(needs, machine)take aMachinefor a runtime that knows more.loader/a-parameter-count-that-does-not-readandloader/a-memory-figure-that-does-not-read. A bare8could be bytes or gigabytes.spec/hardware-fit.yamlholds the readings (counts, amounts, refusals) and the decisions (machine × row → kept or left out, with the sentence). The Rust checker reads its value sections and the Python resolver reads all of it, so both ports read a figure the same way.size:orrequires:yet, because each figure needs a source somebody else can follow. A runtime that measures them writes them on its own copy of the row.Proof
every_size_and_memory_in_the_shared_table_reads_as_it_says,a_figure_that_does_not_read_is_refused_where_it_is_written,every_figure_the_distribution_ships_reads(crates/pact-loader/src/hardware.rs).test_a_local_model_must_fit_the_machine.py(readings and refusals from the shared table, the decision table,satisfiesleaving out a local row the machine cannot hold,this_machinereports memory and no accelerator).tests/golden/schema-fields.txtre-blessed;docs/97-PRIMITIVES.mdtable,site-docs/reference/kinds.md(71 kinds) and counts synced (scripts/sync-counts.sh: 1725 Rust + 3650 adapter after the master merge).cargo test --workspacepasses (1725, counted by sync-counts.sh); the adapter suite has 3619 passed and 30 skipped. One local failure,test_deepeval_comes_with_what_its_benchmarks_import(from A benchmark named in any script, a figure recorded under an alias, and DeepEval's ARC challenge set #42), happened only because the local venv lacks thedeepevalextra'sdatasets. CI installs that extra.Purpose checklist (BMH PACT v97 §0.2)
spec/hardware-fit.yamlcases run in Rust and Python.spec/schema.yamlwith checker codes.🤖 Generated with Claude Code