minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

config: retire ServerArgs.derive; per-runner values are constructor arguments (#33887)

Browse Source
This commit is contained in:
Cheng Wan
2026-08-07 22:41:09 -07:00
committed by GitHub
parent 5dffa06fe1
commit a5af27f49e
12 changed files with 132 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/attention/unittests/hybrid_linear/test_flashinfer_mla_chunk_metadata.py
+3 -2
View File
@@ -46,9 +46,10 @@ class _ChunkKVMLARunner(MockMLAModelRunner):
def __init__(self, **kwargs):
super().__init__(**kwargs)
from sglang.srt.runtime_context import get_context
from sglang.test.test_utils import server_args_variant
self.server_args = self.server_args.derive(
"attention-unittest",
self.server_args = server_args_variant(
self.server_args,
disable_chunked_prefix_cache=False,
flashinfer_mla_disable_ragged=False,
)
test/registered/unit/test_runtime_context.py
+4 -6
View File
@@ -261,9 +261,9 @@ class TestServerArgsScopedOverride(_IsolatedServerArgs):
# unnamed fields keep their dataclass defaults
self.assertEqual(published.tp_size, 1)
def test_fields_carry_provenance(self):
published = get_context().override_server_args(tp_size=4).install()
self.assertIn(("test-override", {"tp_size": 4}), published._runtime_mutations)
def test_unknown_fields_are_rejected(self):
with self.assertRaises(ValueError):
get_context().override_server_args(not_a_config_field=1).install()
def test_restore_reinstates_previous_publish(self):
previous = object()
@@ -299,12 +299,10 @@ class TestServerArgsScopedOverride(_IsolatedServerArgs):
def test_installed_config_arms_the_strict_guard(self):
# The published dummy must behave like a resolved config: bare writes
# raise, and a differing value lives on a derived variant.
# raise.
published = get_context().override_server_args(tp_size=2).install()
with self.assertRaises(AttributeError):
published.tp_size = 4
variant = published.derive("test", tp_size=4)
self.assertEqual(variant.tp_size, 4)
self.assertEqual(published.tp_size, 2)
def test_restore_resets_the_capture_seed(self):
test/registered/unit/test_runtime_context_override.py
+1 -3
View File
@@ -118,9 +118,7 @@ class TestContextOverride(CustomTestCase):
rc.get_context().override(
"ModelRunner.configure_kv_cache_dtype", kv_cache_dtype="fp8_e4m3"
)
draft = ServerArgs(model_path="dummy").derive(
"draft-build", kv_cache_dtype="bf16"
)
draft = ServerArgs(model_path="dummy", kv_cache_dtype="bf16")
with rc.get_context().preserve_config():
rc.get_context().set_server_args(draft)
# Inside the scope the draft's bags are live...
test/registered/unit/test_server_args_derive.py
-79
View File
@@ -1,79 +0,0 @@
"""``ServerArgs.derive`` is the only way one config becomes another.
After resolution the instance is the process's read-only startup record and the
object the config bags were projected from, so it cannot be mutated: a change to
resolved config goes to the bags (``get_context().override``), and a config that
differs for one runner or worker — a draft's context length, an encode worker's
device — is a second object.
"""
from sglang.test.ci.ci_register import register_cpu_ci
register_cpu_ci(est_time=5, suite="base-a-test-cpu")
import unittest
from sglang.srt.runtime_context import get_context, reset_context
from sglang.srt.server_args import ServerArgs
from sglang.test.test_utils import CustomTestCase
class TestServerArgsDerive(CustomTestCase):
def tearDown(self):
reset_context()
def _resolved(self) -> ServerArgs:
"""A config in the post-resolution state, without a real model."""
server_args = ServerArgs(model_path="dummy")
object.__setattr__(server_args, "_declarations_materialized", True)
return server_args
def test_the_receiver_is_untouched(self):
server_args = self._resolved()
variant = server_args.derive("draft_worker.copy", context_length=1024)
self.assertEqual(variant.context_length, 1024)
self.assertIsNot(variant, server_args)
self.assertIsNone(server_args.context_length)
def test_a_published_config_rejects_assignment_but_still_derives(self):
override = get_context().override_server_args(tp_size=2)
published = override.install()
self.addCleanup(override.restore)
with self.assertRaises(AttributeError):
published.tp_size = 4
self.assertEqual(published.derive("worker", tp_size=4).tp_size, 4)
self.assertEqual(published.tp_size, 2)
def test_the_variant_is_not_published_by_deriving(self):
override = get_context().override_server_args(tp_size=2)
published = override.install()
self.addCleanup(override.restore)
published.derive("worker", tp_size=4)
self.assertIs(get_context().server_args, published)
def test_the_variant_is_frozen_too(self):
variant = self._resolved().derive("worker", context_length=1024)
with self.assertRaises(AttributeError):
variant.context_length = 2048
def test_provenance_is_recorded(self):
variant = self._resolved().derive("draft_worker.copy", watchdog_timeout=1.0)
self.assertIn(
("draft_worker.copy", {"watchdog_timeout": 1.0}),
getattr(variant, "_runtime_mutations", []),
)
def test_a_resolvable_field_joins_the_declaration_stash(self):
"""So a re-resolution of the variant keeps the derived value."""
variant = self._resolved().derive("draft_worker.build", kv_cache_dtype="bf16")
stash = getattr(variant, "_resolved_overrides", [])
self.assertIn(("draft_worker.build", {"kv_cache_dtype": "bf16"}), stash)
if __name__ == "__main__":
unittest.main()
test/registered/unit/test_server_args_mutation_ratchet.py
+5 -5
View File
@@ -10,9 +10,9 @@ baseline to lock in the progress.
There is no post-resolution mutation entry point on the instance any more:
resolved config changes go to the context bags via
``get_context().override(source, **fields)``, and a config that differs for one
runner or worker is a separate object built with ``ServerArgs.derive(source,
**fields)``. The baseline is therefore zero. ``ServerArgs.__setattr__`` raises
``get_context().override(source, **fields)``, and a value that differs for one
runner or worker travels as a constructor argument to it. The baseline is
therefore zero. ``ServerArgs.__setattr__`` raises
on a bare assignment after resolution; this ratchet catches the sites the tests
never execute.
"""
@@ -70,8 +70,8 @@ class TestServerArgsMutationRatchet(CustomTestCase):
f"{count} > baseline {_BASELINE}. Configuration is resolved in "
"ServerArgs.__post_init__; declare through the pipeline "
"(passes / declare_load_time_override), change resolved config "
"with get_context().override(source, ...), or build a variant "
"with server_args.derive(source, ...) — do not assign fields."
"with get_context().override(source, ...), or hand the value "
"to its runner as a constructor argument — do not assign fields."
)
if count < _BASELINE:
self.fail(
test/registered/unit/test_server_args_no_instance_mutation_entry.py
+42 -13
View File
@@ -1,13 +1,14 @@
"""``ServerArgs`` has no in-place mutation entry, and nothing calls one.
``ServerArgs.override(source, **fields)`` used to mutate a resolved instance;
after resolution the fields are the record the config bags were projected from,
so such a write desyncs every namespace reader. The method is gone and the two
sanctioned replacements are ``get_context().override`` (post-publish, writes the
bags) and ``ServerArgs.derive`` (a variant for another runner / process). Late
launcher-stage resolution writes in place through
``arg_groups.overrides.declare_late_resolution``, which refuses the published
instance.
``ServerArgs.override(source, **fields)`` used to mutate a resolved instance,
and ``ServerArgs.derive(source, **fields)`` used to copy-and-edit one; after
resolution the fields are the record the config bags were projected from, so a
write desyncs every namespace reader, and a copy invites publishing stale
variants. Both are gone: post-publish changes go to the bags
(``get_context().override``), a value one runner or worker owns travels as a
constructor argument, and late launcher-stage resolution writes in place
through ``arg_groups.overrides.declare_late_resolution``, which refuses the
published instance.
The textual half of this guard matters because the resolution pipeline's own file
is exempt from the mutation ratchet: a ``self.override(...)`` there — exactly
@@ -41,11 +42,19 @@ _EXCLUDED = ("multimodal_gen",)
class TestNoServerArgsMutationEntry(CustomTestCase):
def test_the_method_is_gone(self):
def test_the_methods_are_gone(self):
self.assertFalse(
hasattr(ServerArgs, "override"),
"ServerArgs.override is back; post-publish changes belong on the bags "
"(get_context().override) and per-runner values on a derive() variant.",
"(get_context().override); a value one runner owns travels as a "
"constructor argument.",
)
self.assertFalse(
hasattr(ServerArgs, "derive"),
"ServerArgs.derive is back; a value one runner or worker owns travels "
"as a constructor argument (draft_attention_backend, MMEncoder "
"gpu_id), and test doubles copy via "
"sglang.test.test_utils.server_args_variant.",
)
def test_nothing_calls_an_instance_override(self):
@@ -63,11 +72,31 @@ class TestNoServerArgsMutationEntry(CustomTestCase):
self.fail(
"in-place ServerArgs mutation call-sites:\n"
+ "\n".join(offenders)
+ "\n\nUse get_context().override(source, ...) for resolved config, "
"server_args.derive(source, ...) for a per-runner variant, or "
"declare_late_resolution(...) for pre-publish launcher resolution."
+ "\n\nUse get_context().override(source, ...) for resolved config "
"or declare_late_resolution(...) for pre-publish launcher "
"resolution."
)
def test_nothing_derives(self):
"""A config is never copied-and-edited in the package: a value one
runner consumes travels as a constructor argument, and test doubles
copy via ``server_args_variant`` (test_utils)."""
derive_pattern = re.compile(r"\.derive\(")
offenders = []
for path in sorted(_SGLANG_ROOT.rglob("*.py")):
rel = path.relative_to(_SGLANG_ROOT).as_posix()
if rel.startswith(_EXCLUDED):
continue
source = path.read_text()
for match in derive_pattern.finditer(source):
line = source.count("\n", 0, match.start()) + 1
offenders.append(f"{rel}:{line}")
self.assertFalse(
offenders,
".derive( call-sites in the package (the method no longer exists):\n"
+ "\n".join(offenders),
)
def test_late_resolution_refuses_the_published_config(self):
from sglang.srt.arg_groups.overrides import declare_late_resolution
from sglang.srt.runtime_context import get_context