inferential 0.1.0__tar.gz

inferential-0.1.0/.gitignore

@@ -0,0 +1,17 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+dist/
+build/
+.eggs/
+*.egg
+.venv/
+.env
+.ruff_cache/
+.pytest_cache/
+.mypy_cache/
+
+# Generated protobuf
+inferential/proto/inferential_pb2.py
+inferential/proto/inferential_pb2.pyi

inferential-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

inferential-0.1.0/Makefile

@@ -0,0 +1,14 @@
+.PHONY: proto test lint clean
+
+proto:
+	@bash scripts/gen_proto.sh
+
+test: proto
+	uv run pytest tests/ -v
+
+lint:
+	uv run ruff check inferential/ tests/
+
+clean:
+	find . -type d -name __pycache__ -exec rm -rf {} +
+	rm -f inferential/proto/inferential_pb2.py inferential/proto/inferential_pb2.pyi

inferential-0.1.0/PKG-INFO

@@ -0,0 +1,281 @@
+Metadata-Version: 2.4
+Name: inferential
+Version: 0.1.0
+Summary: Robotics-aware inference orchestration on top of Ray Serve
+Author: inferential.sh
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: numpy>=1.24
+Requires-Dist: protobuf>=5.0
+Requires-Dist: pyzmq>=26.0
+Provides-Extra: dev
+Requires-Dist: grpcio-tools>=1.60; extra == 'dev'
+Requires-Dist: pydantic>=2.0; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ray[serve]>=2.9; extra == 'dev'
+Requires-Dist: ruff>=0.4; extra == 'dev'
+Provides-Extra: server
+Requires-Dist: pydantic>=2.0; extra == 'server'
+Requires-Dist: ray[serve]>=2.9; extra == 'server'
+Description-Content-Type: text/markdown
+
+# Inferential
+
+Multi-client inference orchestration on top of Ray Serve.
+
+Inferential sits between your clients and your ML models. It receives observations over ZMQ, schedules inference requests using cadence-aware priority scoring, dispatches to Ray Serve, and streams results back — all with sub-millisecond transport overhead. Built for any scenario where multiple clients need concurrent access to shared models: robotics fleets, game agents, IoT devices, real-time ML pipelines.
+
+## Features
+
+- **ZMQ transport** — ROUTER/DEALER sockets with automatic reconnection and zero-copy tensor payloads
+- **Pluggable schedulers** — Deadline-aware (default), batch-optimized, priority-tiered, round-robin
+- **Cadence learning** — EMA-based tracking of each client's request pattern to predict urgency
+- **Protobuf wire protocol** — Typed tensor metadata (dtype, shape, encoding) with binary payload
+- **In-memory metrics** — Ring-buffer storage with label filtering and percentile stats (p50/p95/p99)
+- **Flexible client IDs** — String or integer, your choice
+- **Lightweight client SDK** — No Ray dependency; just `pyzmq`, `protobuf`, and `numpy`
+
+## Install
+
+```bash
+# Client SDK only (robot side)
+pip install inferential
+
+# Server with Ray Serve
+pip install inferential[server]
+
+# Development
+pip install inferential[dev]
+```
+
+## Quick Start
+
+### Server
+
+```python
+import asyncio
+from inferential import Server
+
+server = Server(bind="tcp://*:5555", models=["policy-v2"])
+server.use_scheduler("deadline_aware")
+
+@server.on_metric
+def log_latency(name, value, labels):
+    if name == "inference_latency_ms":
+        print(f"Client {labels.get('client')}: {value:.1f}ms")
+
+asyncio.run(server.run())
+```
+
+### Client
+
+```python
+import numpy as np
+from inferential import Connection
+
+conn = Connection(server="tcp://localhost:5555", client_id="agent-01", client_type="sensor")
+model = conn.model("policy-v2", latency_budget_ms=30.0)
+
+# Send observation
+readings = np.array([0.0, -0.78, 0.0, -2.35, 0.0, 1.57, 0.78], dtype=np.float32)
+model.observe(
+    urgency=0.8,
+    sensor_readings=readings,
+    prompt="classify anomaly",  # strings go to metadata
+)
+
+# Get action
+result = model.get_result(timeout_ms=50)
+if result is not None:
+    output = result["actions"]  # np.ndarray
+```
+
+## Observation API
+
+`model.observe()` accepts any combination of keyword arguments:
+
+- **`np.ndarray`** values are serialized as tensors with full dtype/shape metadata
+- **`str`** values are passed as metadata key-value pairs
+- **`urgency`** (float, 0.0–1.0) — hints how time-critical this request is
+- **`steps_remaining`** (int, optional) — remaining steps in the current trajectory
+
+```python
+# Multi-modal observation
+model.observe(
+    urgency=0.5,
+    steps_remaining=120,
+    state_vector=np.zeros(7, dtype=np.float32),
+    image=np.zeros((3, 224, 224), dtype=np.uint8),
+    prompt="describe the scene",
+)
+```
+
+## Schedulers
+
+Four built-in strategies, selectable via config or at runtime:
+
+| Strategy | Description |
+|----------|-------------|
+| `deadline_aware` | Weighted scoring: cadence, urgency, priority, age (default) |
+| `batch_optimized` | Groups requests per model, flushes on size or time |
+| `priority_tiered` | Strict priority tiers, FIFO within each tier |
+| `round_robin` | Fair rotation across clients |
+
+```python
+from inferential.scheduler.base import create_scheduler
+from inferential.config.schema import SchedulingConfig
+
+# Standalone usage — no server needed
+scheduler = create_scheduler(SchedulingConfig(strategy="batch_optimized"))
+scheduler.submit(request)
+batch = scheduler.next_batch()
+```
+
+The server wraps this and lets you swap strategies at runtime:
+
+```python
+server.use_scheduler("deadline_aware", cadence_weight=50.0, urgency_weight=30.0)
+```
+
+### Custom Scoring Policy
+
+Override how the deadline-aware scheduler scores requests:
+
+```python
+from inferential import register_policy, InferenceRequest
+
+@register_policy("safety_first")
+def score(req: InferenceRequest) -> float:
+    if req.urgency > 0.9:
+        return 1000.0
+    return req.priority * 10.0
+
+server.use_scheduler("deadline_aware", policy="safety_first")
+```
+
+### Custom Scheduler
+
+Implement the `Scheduler` interface and register it:
+
+```python
+from inferential.scheduler.base import Scheduler, register_scheduler
+
+@register_scheduler("my_scheduler")
+class MyScheduler(Scheduler):
+    def __init__(self, config):
+        self._queue = []
+
+    def submit(self, request):
+        self._queue.append(request)
+
+    def next_batch(self):
+        batch, self._queue = self._queue[:8], self._queue[8:]
+        return batch
+
+    def tick(self):
+        pass
+
+    def status(self):
+        return {"queue_len": len(self._queue)}
+
+    def queue_len(self):
+        return len(self._queue)
+
+server.use_scheduler("my_scheduler")
+```
+
+## Metrics
+
+```python
+# Query stats over a time window
+stats = server.metrics.get_stats("inference_latency_ms", window_seconds=60)
+print(f"p95 latency: {stats.p95:.1f}ms")
+
+# Latest value
+depth = server.metrics.get_latest("queue_depth")
+
+# Full snapshot of all metrics
+snapshot = server.metrics.snapshot()
+```
+
+Tracked metrics: `inference_latency_ms`, `observation_staleness_ms`, `payload_size_bytes`, `queue_depth`, `queue_full_drops`, `dispatch_errors`, `dispatch_retries`, `requests_expired`, `active_clients`, `observation_errors`.
+
+## Queue Management
+
+The scheduler queue supports TTL, overflow policies, and dispatch retry:
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `request_ttl_ms` | 5000 | Drop queued requests older than this (avoids wasting GPU on stale data) |
+| `overflow_policy` | `"drop_oldest"` | What to do when the queue is full: `"drop_oldest"` evicts the stalest request, `"reject_newest"` drops the incoming one |
+| `max_retries` | 0 | Re-queue failed dispatches up to N times before dropping |
+
+```python
+server.use_scheduler(
+    "deadline_aware",
+    request_ttl_ms=2000,           # 2s TTL
+    overflow_policy="drop_oldest", # keep fresh data, discard stale
+    max_retries=2,                 # retry transient failures twice
+)
+```
+
+## Configuration
+
+```python
+from inferential.config import InferentialConfig
+
+config = InferentialConfig(
+    transport={"bind": "tcp://*:5555", "recv_hwm": 2000},
+    scheduling={
+        "strategy": "deadline_aware",
+        "max_queue_size": 500,
+        "request_ttl_ms": 3000,
+        "overflow_policy": "drop_oldest",
+        "max_retries": 1,
+    },
+    clients={
+        "defaults": {"latency_budget_ms": 50.0, "priority": 1},
+        "known": [
+            {"id": "agent-01", "model": "policy-v2", "latency_budget_ms": 30.0, "priority": 2},
+        ],
+        "accept_unknown": True,
+    },
+    response_tracking={"cadence_alpha": 0.3, "disconnect_timeout_s": 10.0},
+    metrics={"ring_buffer_size": 10000},
+)
+
+server = Server(config=config)
+```
+
+## Wire Protocol
+
+Messages use protobuf serialization over ZMQ multipart frames:
+
+```
+[identity | "" | envelope (protobuf) | payload (binary tensors)]
+```
+
+- **Observation** (client -> server): client info, model ID, urgency, tensor descriptors, metadata
+- **ModelResponse** (server -> client): response ID, inference latency, output tensors, metadata
+
+Supported tensor dtypes: `float16`, `float32`, `float64`, `bfloat16`, `uint8`, `int32`, `int64`, `bool`.
+Supported encodings: `raw`, `jpeg`, `png`.
+
+## Development
+
+```bash
+# Generate protobuf code
+make proto
+
+# Run tests
+make test
+
+# Lint
+make lint
+```
+
+## License
+
+Apache-2.0