feat: checkpoint distributed gguf runtime stories

This commit is contained in:
Dobromir Popov
2026-07-15 23:42:58 +03:00
parent eaf00f6add
commit 1fe31ef38d
60 changed files with 8478 additions and 105 deletions

View File

@@ -42,9 +42,12 @@ def _report(**overrides):
status="passed",
duration_ms=142,
validated_at=1_760_000_000.0,
owns_embedding=True,
owns_final_head=False,
)
kwargs.update(overrides)
return build_capability_report(**kwargs)
report = build_capability_report(**kwargs)
return report
# --- model-agnostic identity ------------------------------------------------
@@ -114,6 +117,9 @@ def test_report_dict_has_the_stable_documented_key_set():
"shard",
"recipe",
"backend",
"artifact",
"runtime_recipe",
"compatibility_fingerprint",
"status",
"validated_at",
"duration_ms",
@@ -121,12 +127,38 @@ def test_report_dict_has_the_stable_documented_key_set():
}
assert payload["schema_version"] == CAPABILITY_SCHEMA_VERSION
assert set(payload["model"]) == {"model_id", "revision", "config_fingerprint"}
assert set(payload["shard"]) == {"start", "end"}
assert set(payload["shard"]) == {
"start",
"end",
"owns_embedding",
"owns_final_head",
}
assert set(payload["recipe"]) == {
"recipe_id",
"recipe_version",
"catalogue_version",
}
assert set(payload["artifact"]) == {
"model_id",
"revision",
"artifact_hash",
"shard_start",
"shard_end",
}
assert set(payload["runtime_recipe"]) == {
"weight_quantization",
"activation_dtype",
"compute_dtype",
"kv_dtype",
"kv_layout",
"tokenizer_revision",
"architecture_adapter",
"backend_id",
"runtime_version",
"boundary_schema_version",
"cache_layout",
"fingerprint",
}
assert set(payload["backend"]) == {
"backend_id",
"device",
@@ -134,10 +166,19 @@ def test_report_dict_has_the_stable_documented_key_set():
"quantization",
"runtime",
}
assert payload["compatibility_fingerprint"].startswith("sha256:")
# JSON-serializable end to end.
assert json.loads(json.dumps(payload)) == payload
def test_report_carries_endpoint_ownership():
"Endpoint ownership is recorded alongside the shard range.\n\nTags: node, startup"
payload = _report().to_dict()
assert payload["shard"]["owns_embedding"] is True
assert payload["shard"]["owns_final_head"] is False
def test_identity_key_pins_model_shard_recipe_and_backend():
"Identity key pins model shard recipe and backend\n\nTags: node, startup"
base = _report()
@@ -156,6 +197,15 @@ def test_identity_key_pins_model_shard_recipe_and_backend():
assert _report(device="other-device").identity_key() != base.identity_key()
def test_compatibility_fingerprint_changes_when_the_runtime_recipe_changes():
"The compatibility fingerprint changes when the runtime recipe changes.\n\nTags: node, startup"
base = _report()
altered = _report(cache_layout="stateless")
assert base.compatibility_fingerprint != altered.compatibility_fingerprint
assert base.runtime_recipe.fingerprint != altered.runtime_recipe.fingerprint
def test_config_fingerprint_is_stable_under_key_order_and_detects_change():
"Config fingerprint is stable under key order and detects change\n\nTags: node, startup"
a = config_fingerprint({"num_hidden_layers": 8, "hidden_size": 512})