[Serve] Add `label_selector` and `bundle_label_selector` to Serve API #57694

ryanaoleary · 2025-10-14T07:06:38Z

Why are these changes needed?

This PR adds the label_selector option to the supported list of Actor options for a Serve deployment. Additionally, we add bundle_label_selector to specify label selectors for bundles when placement_group_bundles are specified for the deployment. These two options are already supported for Tasks/Actors and placement groups respectively.

Example use case:

llm_config = LLMConfig(
    model_loading_config={
        "model_id": "meta-llama/Meta-Llama-3-70B-Instruct",
        "model_source": "huggingface",
    },
    engine_kwargs=tpu_engine_config,
    resources_per_bundle={"TPU": 4},
    runtime_env={"env_vars": {"VLLM_USE_V1": "1"}},
    deployment_config={
        "num_replicas": 4,
        "ray_actor_options": {
            # In a GKE cluster with multiple TPU node-pools, schedule
            # only to the desired slice.
            "label_selector": {
                "ray.io/tpu-topology": "4x4" # added by default by Ray
            }
        }
    }
)

The expected behaviors of these new fields is as follows:

Pack scheduling enabled

PACK/STRICT_PACK PG strategy:

Standard PG without bundle_label_selector or fallback:
- Sorts replicas by resource size (descending). Attempts to find the "best fit" node (minimizing fragmentation) that has available resources. Creates a Placement Group on that target node.
PG node label selector provided:
- Same behavior as regular placement group but filters the list of candidate nodes to only those matching the label selector before finding the best fit
PG node label selector and fallback:
Same as above but when scheduling tries the following:
1. Tries to find a node matching the primary placement_group_bundles and bundle_label_selector.
2. If no node fits, iterates through the placement_group_fallback_strategy. For each fallback entry, tries to find a node matching that entry's bundles and labels.
3. If a node is found, creates a PG on it.

SPREAD/STRICT_SPREAD PG strategy:

If any deployment uses these strategies, the global logic falls back to "Spread Scheduling" (see below)

Spread scheduling enabled

Standard PG without bundle_label_selector or fallback:
- Creates a Placement Group via Ray Core without specifying a target_node_id. Ray Core decides placement based on the strategy.
PG node label selector provided:
- Serve passes the bundle_label_selector to the CreatePlacementGroupRequest. Ray Core handles the soft/hard constraint logic during PG creation.
PG node label selector and fallback:
- Serve passes the bundle_label_selector to the CreatePlacementGroupRequest, fallback_strategy is not yet supported in the placement group options so this field isn't passed / considered. It's only used in the "best fit" node selection logic which is skipped for Spread scheduling.

Related issue number

#51564

Checks

I've signed off every commit(by using the -s flag, i.e., git commit -s) in this PR.
I've run pre-commit jobs to lint the changes in this PR. (pre-commit setup)
I've included any doc changes needed for https://docs.ray.io/en/master/.
- I've added any new APIs to the API Reference. For example, if I added a
  method in Tune, I've added it in doc/source/tune/api/ under the
  corresponding .rst file.
I've made sure the tests are passing. Note that there might be a few flaky tests, see the recent failures at https://flakey-tests.ray.io/
Testing Strategy
- Unit tests
- Release tests
- This PR is not tested :(

Signed-off-by: Ryan O'Leary <[email protected]>

ryanaoleary · 2025-10-14T07:10:43Z

cc: @MengjinYan @eicherseiji I think this change can help enable TPU use-cases with Ray LLM, since it'll allow users to target the desired slice/topology based on labels like these:

ray.io/accelerator-type: TPU-V6E
ray.io/node-group: tpu-group
ray.io/node-id: 0870a6a06413aed6079c15eeaa4f61e8a1413fa6140fc70c93608505
ray.io/tpu-pod-type: v6e-16
ray.io/tpu-slice-name: tpu-group-0
ray.io/tpu-topology: 4x4
ray.io/tpu-worker-id: '2'

MengjinYan

The current change looks good.

At the same time, I have a general question, probably also to @eicherseiji as well: I'm not familiar with the serve codebase. But from the look at the code, the change in the PR seems not cover the whole code path from the replica config to actually creating the placement group where we need to apply the bundle label selector (e.g. CreatePlacementGroupRequest, DeploymentTargetState, DeploymentVersion, etc.).

Wondering if we should include the change to the rest of the code path in this PR as well?

python/ray/serve/_private/config.py

eicherseiji · 2025-10-16T01:19:10Z

Hi @ryanaoleary! Seems like it may be useful, but could you go into more detail about the problem this solved for you? I.e. is it typical to have multiple TPU node pools/heterogeneous compute in a TPU cluster?

Signed-off-by: Ryan O'Leary <[email protected]>

ryanaoleary · 2025-10-16T04:29:00Z

Hi @ryanaoleary! Seems like it may be useful, but could you go into more detail about the problem this solved for you? I.e. is it typical to have multiple TPU node pools/heterogeneous compute in a TPU cluster?

The use-case would be for TPU multi-slice, where it's important that the Ray nodes reserved with some group of resources (i.e. a bundle of TPUs) are a part of the same actual TPU slice so that they can benefit from the high speed ICI interconnects. There are GKE webhooks that set some TPU information as env vars when the Pods are created, including topology and a unique identifier for the slice which we set as Ray node labels. They also inject podAffinities so that the TPU Pods are scheduled to the same node-pool (i.e. TPU slice) and co-located. So if we then use those labels for scheduling in the application code, we can guarantee that the workers are running on co-located TPU devices.

For a RayCluster with multiple TPU slices (of the same topology or different), we currently only schedule using TPU: <number-resources> and/or the TPU generation (i.e. TPU-V6E) which can result in the placement group spanning across TPU slices.

eicherseiji · 2025-10-16T16:50:10Z

@ryanaoleary I see, thanks! Is there a reason we can't extend/re-use the resources_per_bundle concept for this instead?

MengjinYan · 2025-10-16T16:55:05Z

Hi @ryanaoleary! Seems like it may be useful, but could you go into more detail about the problem this solved for you? I.e. is it typical to have multiple TPU node pools/heterogeneous compute in a TPU cluster?

In addition to the TPU support, in general, we want to have label support in all library APIs so that user can do scheduling based on node labels as well.

ryanaoleary · 2025-10-16T17:19:09Z

@ryanaoleary I see, thanks! Is there a reason we can't extend/re-use the resources_per_bundle concept for this instead?

I think just configuring resources_per_bundle with a TPU resource alone wouldn't work, we'd have to add some matching custom resource that denotes the TPU slice name to Pods of the same slice and use it as a workaround. That would also work, but moving away from this workaround was one of the rationales for adding label selectors. Additionally, we already set these Ray node labels for TPUs by default so it'd be less work for the user to get it working.

github-actions · 2025-10-31T00:38:00Z

This pull request has been automatically marked as stale because it has not had
any activity for 14 days. It will be closed in another 14 days if no further activity occurs.
Thank you for your contributions.

You can always ask for help on our discussion forum or Ray's public slack channel.

If you'd like to keep this open, just leave any comment, and the stale label will be removed.

python/ray/serve/_private/config.py

python/ray/serve/tests/test_api.py

abrarsheikh · 2025-12-04T07:04:26Z

@ryanaoleary I will review this PR next week

ktyxx · 2025-12-09T11:09:46Z

thanks for working on this! Really looking forward to using label selectors in Serve.
One thing I was wondering - would it be possible to also expose fallback_strategy from ray core?
My use case is that I'd like to use labels more as a "preference" rather than a strict requirement. For example, I want to prioritize deploying to nodes with a specific label, but if none are available, just fall back to any node (like the default scheduling behavior). I actually opened an issue about this before (#59055) - initially thinking about using NodeLabelSchedulingStrategy with hard/soft params, but was told it's being deprecated in favor of label selectors. So it'd be great if Serve could also expose fallback_strategy to support soft constraints via fallback_strategy=[{"label_selector": {}}] pattern.
What do you think?

Signed-off-by: ryanaoleary <[email protected]>

ryanaoleary · 2026-01-08T04:16:03Z

the def schedule function is hard to follow/review right now, probably also because I am not 100% sure what the expected behavior is under various situations. could you fill out the following situations and add it to the PR description

Pack scheduling enabled

PG strategy pack/strict-pack/spread/strict-spread

PG node label selector provided vs when not provided

PG node label fallback provided vs when not provided

spread scheduling enabled

PG strategy pack/strict-pack/spread/strict-spread

PG node label selector provided vs when not provided

PG node label fallback provided vs when not provided

@abrarsheikh Done, I updated the PR description with an outline that I think covers all these situations.

python/ray/serve/_private/deployment_scheduler.py

abrarsheikh · 2026-01-08T06:56:26Z

I think the logic of your implementation is correct afaict, I am writing down my understanding of how this stuff is supposed to work, so that we both are on the same page

Decision Flow Chart For Scheduler

Is RAY_SERVE_USE_PACK_SCHEDULING_STRATEGY=1?
├── No → Use Spread Scheduling (Ray Core decides placement)
└── Yes
    └── Any deployment uses non-STRICT_PACK PG?
        ├── Yes → Use Spread Scheduling (Ray Core decides placement)
        └── No → Use Pack Scheduling
            └── For each replica:
                ├── Has PG bundles?
                │   ├── Yes (must be STRICT_PACK)
                │   │   ├── Has bundle_label_selector?
                │   │   │   ├── Yes → Filter nodes by ALL selectors, find best-fit
                │   │   │   └── No → Find best-fit node for sum of bundles
                │   │   └── Create PG with _soft_target_node_id + bundle_label_selector
                │   └── No (Actor only)
                │       ├── Has label_selector?
                │       │   ├── Yes → Filter nodes, find best-fit
                │       │   └── No → Find best-fit node
                │       ├── Has fallback_strategy?
                │       │   └── Yes → Try each fallback's labels until match
                │       └── Create actor with NodeAffinitySchedulingStrategy
                └── Pass to Ray Core for final placement

Configuration	Scheduling Mode	Serve Node Selection	Ray Core Strategy
Actor only	Pack	Best-fit	`NodeAffinitySchedulingStrategy`
Actor + label_selector	Pack	Best-fit with label filter	`NodeAffinitySchedulingStrategy`
Actor + label_selector + fallback	Pack	Try labels in order	`NodeAffinitySchedulingStrategy`
STRICT_PACK PG	Pack	Best-fit for sum of bundles	`PlacementGroupSchedulingStrategy` with `_soft_target_node_id`
STRICT_PACK PG + bundle_label_selector	Pack	Best-fit for sum of bundles, with label filter	`PlacementGroupSchedulingStrategy` with `_soft_target_node_id` + `bundle_label_selector`
PACK/SPREAD/STRICT_SPREAD PG	Spread	None	`PlacementGroupSchedulingStrategy` (Ray Core decides)
Any + `placement_group_fallback_strategy`	N/A	N/A	`NotImplementedError`

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

python/ray/serve/_private/deployment_scheduler.py

python/ray/serve/_private/deployment_state.py

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

python/ray/serve/_private/deployment_scheduler.py

python/ray/serve/tests/unit/test_deployment_scheduler.py

Signed-off-by: ryanaoleary <[email protected]>

python/ray/serve/tests/test_deployment_version.py

python/ray/serve/tests/unit/test_application_state.py

python/ray/serve/_private/deployment_scheduler.py

Signed-off-by: ryanaoleary <[email protected]>

python/ray/serve/tests/unit/test_application_state.py

Signed-off-by: ryanaoleary <[email protected]>

abrarsheikh · 2026-01-09T17:46:36Z

python/ray/_private/label_utils.py

+        return False
+
+    # !in operator
+    if selector_value.startswith("!in(") and selector_value.endswith(")"):


should we trim the selector_value before passing through the string parsers?

abrarsheikh · 2026-01-09T17:55:10Z

python/ray/serve/_private/deployment_scheduler.py

+            # Actor: Use Actor label selector
+            if "label_selector" in scheduling_request.actor_options:
+                primary_labels = [
+                    scheduling_request.actor_options["label_selector"] or {}


is None allowed in actor_options["label_selector"]?

abrarsheikh · 2026-01-09T17:58:33Z

python/ray/serve/_private/deployment_scheduler.py

+                fallback_labels = [fallback.get("label_selector", {}) or {}]
+                placement_candidates.append(
+                    (scheduling_request.required_resources, fallback_labels)
+                )


can there be a fallback with label_selector == None?

Also should we skip adding to placement_candidates if fallback_labels is empty?

abrarsheikh · 2026-01-09T18:10:32Z

python/ray/tests/test_label_utils.py

+@pytest.mark.parametrize(
+    "node_value, selector_value, expected",
+    [
+        # Equals operator
+        ("us-west", "us-west", True),
+        ("us-east", "us-west", False),
+        (None, "us-west", False),
+        # Not equals (!) operator
+        ("us-west", "!us-east", True),
+        ("us-east", "!us-east", False),
+        (None, "!us-east", True),
+        # In operator
+        ("A100", "in(A100, H100)", True),
+        ("T4", "in(A100, H100)", False),
+        (None, "in(A100, H100)", False),
+        ("value", "in(value)", True),
+        # Not in operator
+        ("T4", "!in(A100, H100)", True),
+        ("A100", "!in(A100, H100)", False),
+        (None, "!in(A100, H100)", True),
+        # Invalid types
+        ("A100", None, False),
+        ("A100", 123, False),
+    ],
+)
+def test_match_label_selector_value(node_value, selector_value, expected):
+    assert match_label_selector_value(node_value, selector_value) == expected
+
+
+@pytest.mark.parametrize(
+    "node_labels, selector, expected",
+    [
+        # Match all
+        (
+            {"region": "us-west", "gpu": "A100"},
+            {"region": "us-west", "gpu": "A100"},
+            True,
+        ),
+        # Partial match
+        (
+            {"region": "us-west", "gpu": "T4"},
+            {"region": "us-west", "gpu": "A100"},
+            False,
+        ),
+        # Multiple operators
+        (
+            {"region": "us-west", "env": "prod"},
+            {"region": "in(us-west, us-east)", "env": "!dev"},
+            True,
+        ),
+        # Missing keys in node labels
+        ({"region": "us-west"}, {"gpu": "!in(H100)"}, True),
+        ({"region": "us-west"}, {"gpu": "in(H100)"}, False),
+    ],
+)
+def test_match_label_selector(node_labels, selector, expected):
+    assert match_label_selector(node_labels, selector) == expected


Suggested change

@pytest.mark.parametrize(

"node_value, selector_value, expected",

[

# Equals operator

("us-west", "us-west", True),

("us-east", "us-west", False),

(None, "us-west", False),

# Not equals (!) operator

("us-west", "!us-east", True),

("us-east", "!us-east", False),

(None, "!us-east", True),

# In operator

("A100", "in(A100, H100)", True),

("T4", "in(A100, H100)", False),

(None, "in(A100, H100)", False),

("value", "in(value)", True),

# Not in operator

("T4", "!in(A100, H100)", True),

("A100", "!in(A100, H100)", False),

(None, "!in(A100, H100)", True),

# Invalid types

("A100", None, False),

("A100", 123, False),

],

)

def test_match_label_selector_value(node_value, selector_value, expected):

assert match_label_selector_value(node_value, selector_value) == expected

@pytest.mark.parametrize(

"node_labels, selector, expected",

[

# Match all

(

{"region": "us-west", "gpu": "A100"},

{"region": "us-west", "gpu": "A100"},

True,

),

# Partial match

(

{"region": "us-west", "gpu": "T4"},

{"region": "us-west", "gpu": "A100"},

False,

),

# Multiple operators

(

{"region": "us-west", "env": "prod"},

{"region": "in(us-west, us-east)", "env": "!dev"},

True,

),

# Missing keys in node labels

({"region": "us-west"}, {"gpu": "!in(H100)"}, True),

({"region": "us-west"}, {"gpu": "in(H100)"}, False),

],

)

def test_match_label_selector(node_labels, selector, expected):

assert match_label_selector(node_labels, selector) == expected

@pytest.mark.parametrize(

"node_value, selector_value, expected",

[

# Equals operator

("us-west", "us-west", True),

("us-east", "us-west", False),

(None, "us-west", False),

# Equals with empty strings

("", "", True),

("value", "", False),

("", "value", False),

# Not equals (!) operator

("us-west", "!us-east", True),

("us-east", "!us-east", False),

(None, "!us-east", True),

# Not equals with empty string

("value", "!", True), # !<empty> means not equal to empty

("", "!", False), # empty string equals empty, so !empty is False

("", "!value", True), # empty string != "value"

# In operator

("A100", "in(A100, H100)", True),

("T4", "in(A100, H100)", False),

(None, "in(A100, H100)", False),

("value", "in(value)", True),

# In operator without spaces

("A100", "in(A100,H100)", True),

("H100", "in(A100,H100)", True),

("T4", "in(A100,H100)", False),

# In operator with many values

("c", "in(a, b, c, d, e)", True),

("z", "in(a, b, c, d, e)", False),

# In operator with empty string value not in list

("", "in(A100, H100)", False),

# Not in operator

("T4", "!in(A100, H100)", True),

("A100", "!in(A100, H100)", False),

(None, "!in(A100, H100)", True),

# Not in operator without spaces

("T4", "!in(A100,H100)", True),

("A100", "!in(A100,H100)", False),

# Not in with single value

("T4", "!in(A100)", True),

("A100", "!in(A100)", False),

# Not in with empty string

("", "!in(A100, H100)", True), # empty string not in list

# Invalid selector types

("A100", None, False),

("A100", 123, False),

(None, None, False),

("value", [], False),

("value", {}, False),

# Node value that looks like operator syntax (edge case)

("in(x)", "in(x)", True),

("!value", "!value", True),

# Case sensitivity

("A100", "a100", False),

("A100", "in(a100, h100)", False),

("A100", "!a100", True),

],

)

def test_match_label_selector_value(node_value, selector_value, expected):

assert match_label_selector_value(node_value, selector_value) == expected

@pytest.mark.parametrize(

"node_labels, selector, expected",

[

# Empty cases

({}, {}, True), # Empty selector matches everything

({"region": "us-west"}, {}, True), # Empty selector matches any node

({}, {"region": "us-west"}, False), # Missing key with equals fails

({}, {"region": "!us-west"}, True), # Missing key with not-equals succeeds

# Match all

(

{"region": "us-west", "gpu": "A100"},

{"region": "us-west", "gpu": "A100"},

True,

),

# Single key match

({"region": "us-west"}, {"region": "us-west"}, True),

({"region": "us-east"}, {"region": "us-west"}, False),

# Partial match (one key matches, one doesn't)

(

{"region": "us-west", "gpu": "T4"},

{"region": "us-west", "gpu": "A100"},

False,

),

# Multiple operators

(

{"region": "us-west", "env": "prod"},

{"region": "in(us-west, us-east)", "env": "!dev"},

True,

),

# Multiple operators - failure case

(

{"region": "us-west", "env": "dev"},

{"region": "in(us-west, us-east)", "env": "!dev"},

False,

),

# Missing keys in node labels

({"region": "us-west"}, {"gpu": "!in(H100)"}, True),

({"region": "us-west"}, {"gpu": "in(H100)"}, False),

({"region": "us-west"}, {"gpu": "!H100"}, True), # Missing key with ! succeeds

# Extra keys in node_labels that selector doesn't care about

(

{"region": "us-west", "gpu": "A100", "env": "prod", "zone": "a"},

{"region": "us-west"},

True,

),

# All keys matching with mixed operators

(

{"region": "us-west", "gpu": "A100", "env": "prod"},

{"region": "us-west", "gpu": "in(A100, H100)", "env": "!dev"},

True,

),

# First key matches, second doesn't

(

{"region": "us-west", "gpu": "T4"},

{"region": "in(us-west, us-east)", "gpu": "in(A100, H100)"},

False,

),

# First key doesn't match

(

{"region": "eu-west", "gpu": "A100"},

{"region": "in(us-west, us-east)", "gpu": "in(A100, H100)"},

False,

),

# Empty string values

({"region": ""}, {"region": ""}, True),

({"region": "us-west"}, {"region": ""}, False),

# Complex multi-key scenario

(

{"cloud": "aws", "region": "us-west", "gpu": "A100", "spot": "true"},

{"cloud": "!gcp", "region": "in(us-west, us-east)", "gpu": "A100"},

True,

),

],

)

def test_match_label_selector(node_labels, selector, expected):

assert match_label_selector(node_labels, selector) == expected

just add more params

abrarsheikh · 2026-01-09T18:15:30Z

python/ray/serve/tests/conftest.py

+        "labels": {"region": "us-east", "gpu-type": "H100"},
+    }
+    cluster.add_node(**node2_config)
+    node_2_id = ray.get(_get_node_id.options(resources={"worker2": 1}).remote())


this is clever, nice :)

abrarsheikh · 2026-01-09T18:33:20Z

python/ray/serve/tests/test_deployment_scheduler.py


        serve.shutdown()




let's add a few more tests here

STRICT_PACK PG + bundle_label_selector (Pack Scheduling Mode)

STRICT_SPREAD PG Strategy

placement_group_fallback_strategy → NotImplementedError

Non-STRICT_PACK PG Forces Spread Mode (when RAY_SERVE_USE_PACK_SCHEDULING_STRATEGY=1)

Multiple Bundles with bundle_label_selector

Actor label_selector + fallback with Multiple Fallbacks

Add label_selector and bundle_label_selector to Serve API

ab6cd99

Signed-off-by: Ryan O'Leary <[email protected]>

ryanaoleary marked this pull request as ready for review October 14, 2025 07:08

ryanaoleary requested a review from a team as a code owner October 14, 2025 07:08

This comment was marked as outdated.

Sign in to view

ray-gardener bot added serve Ray Serve Related Issue community-contribution Contributed by the community labels Oct 14, 2025

ryanaoleary mentioned this pull request Oct 14, 2025

[Core] Ray Label Selector API Implementation Tracker #51564

Open

35 tasks

eicherseiji self-requested a review October 14, 2025 23:21

MengjinYan added the go add ONLY when ready to merge, run all tests label Oct 15, 2025

MengjinYan reviewed Oct 15, 2025

View reviewed changes

python/ray/serve/_private/config.py Outdated Show resolved Hide resolved

MengjinYan assigned MengjinYan and eicherseiji Oct 15, 2025

Fix argument order

0a449e1

Signed-off-by: Ryan O'Leary <[email protected]>

github-actions bot added the stale The issue is stale. It will be closed within 7 days unless there are further conversation label Oct 31, 2025

Merge branch 'master' into add-label-selector-serve-option

a900e41

github-actions bot added unstale A PR that has been marked unstale. It will not get marked stale again if this label is on it. and removed stale The issue is stale. It will be closed within 7 days unless there are further conversation labels Nov 4, 2025

Merge branch 'master' into add-label-selector-serve-option

6862eee

cursor bot reviewed Nov 5, 2025

View reviewed changes

python/ray/serve/_private/config.py Outdated Show resolved Hide resolved

zcin reviewed Nov 5, 2025

View reviewed changes

python/ray/serve/_private/config.py Outdated Show resolved Hide resolved

python/ray/serve/tests/test_api.py Outdated Show resolved Hide resolved

abrarsheikh mentioned this pull request Dec 4, 2025

[Serve] Support hard node label constraints in deployment scheduling #59055

Open

ryanaoleary and others added 3 commits January 8, 2026 03:07

Fix explicit null bundles in fallback causes crash

4a771c1

Signed-off-by: ryanaoleary <[email protected]>

Add validation test for validate_bundle_label_selector

5fc10e7

Signed-off-by: ryanaoleary <[email protected]>

Merge branch 'master' into add-label-selector-serve-option

0b294cc

ryanaoleary requested a review from abrarsheikh January 8, 2026 04:16

abrarsheikh reviewed Jan 8, 2026

View reviewed changes

ryanaoleary and others added 4 commits January 7, 2026 23:41

Update python/ray/serve/_private/deployment_scheduler.py

cb78cc2

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

a55af8e

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

5e8f85e

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

3128161

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

cursor bot reviewed Jan 8, 2026

View reviewed changes

python/ray/serve/_private/deployment_scheduler.py Show resolved Hide resolved

python/ray/serve/_private/deployment_scheduler.py Show resolved Hide resolved

python/ray/serve/_private/deployment_state.py Show resolved Hide resolved

ryanaoleary and others added 5 commits January 8, 2026 03:03

Update python/ray/serve/_private/deployment_scheduler.py

51dd705

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

45dd5aa

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

c213408

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

dc59988

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

Update python/ray/serve/_private/deployment_scheduler.py

fc79d5a

Co-authored-by: Abrar Sheikh <[email protected]> Signed-off-by: Ryan O'Leary <[email protected]>

cursor bot reviewed Jan 8, 2026

View reviewed changes

ryanaoleary and others added 4 commits January 9, 2026 00:52

Fix naming from suggested comments

802bd5e

Signed-off-by: ryanaoleary <[email protected]>

Fix version truthiness check

cde9d08

Signed-off-by: ryanaoleary <[email protected]>

Merge branch 'master' into add-label-selector-serve-option

656986d

Move filter by label selector logic to label_utils

010827f

Signed-off-by: ryanaoleary <[email protected]>

ryanaoleary requested a review from a team as a code owner January 9, 2026 01:56

Merge branch 'master' into add-label-selector-serve-option

1e3a074

cursor bot reviewed Jan 9, 2026

View reviewed changes

python/ray/serve/tests/test_deployment_version.py Outdated Show resolved Hide resolved

python/ray/serve/tests/unit/test_application_state.py Outdated Show resolved Hide resolved

python/ray/serve/_private/deployment_scheduler.py Outdated Show resolved Hide resolved

Fix key names and add NotImplementedError

89d4390

Signed-off-by: ryanaoleary <[email protected]>

ryanaoleary requested a review from abrarsheikh January 9, 2026 02:33

cursor bot reviewed Jan 9, 2026

View reviewed changes

python/ray/serve/tests/unit/test_application_state.py Show resolved Hide resolved

Fix test key

bc76515

Signed-off-by: ryanaoleary <[email protected]>

abrarsheikh reviewed Jan 9, 2026

View reviewed changes

[Serve] Add label_selector and bundle_label_selector to Serve API #57694

Are you sure you want to change the base?

[Serve] Add label_selector and bundle_label_selector to Serve API #57694

Uh oh!

Conversation

ryanaoleary commented Oct 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Why are these changes needed?

Pack scheduling enabled

Spread scheduling enabled

Related issue number

Checks

Uh oh!

ryanaoleary commented Oct 14, 2025

Uh oh!

This comment was marked as outdated.

Uh oh!

MengjinYan left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

eicherseiji commented Oct 16, 2025

Uh oh!

ryanaoleary commented Oct 16, 2025

Uh oh!

eicherseiji commented Oct 16, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

MengjinYan commented Oct 16, 2025

Uh oh!

ryanaoleary commented Oct 16, 2025

Uh oh!

github-actions bot commented Oct 31, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

abrarsheikh commented Dec 4, 2025

Uh oh!

ktyxx commented Dec 9, 2025

Uh oh!

ryanaoleary commented Jan 8, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

abrarsheikh commented Jan 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Decision Flow Chart For Scheduler

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

abrarsheikh Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

abrarsheikh Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

abrarsheikh Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

abrarsheikh Jan 9, 2026

Choose a reason for hiding this comment

Uh oh!

[Serve] Add `label_selector` and `bundle_label_selector` to Serve API #57694

[Serve] Add `label_selector` and `bundle_label_selector` to Serve API #57694

ryanaoleary commented Oct 14, 2025 •

edited

Loading

eicherseiji commented Oct 16, 2025 •

edited

Loading

abrarsheikh commented Jan 8, 2026 •

edited

Loading