kachedb 0.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- kachedb-0.1.0/.github/ISSUE_TEMPLATE/bug_report.yml +40 -0
- kachedb-0.1.0/.github/ISSUE_TEMPLATE/feature_request.yml +28 -0
- kachedb-0.1.0/.github/PULL_REQUEST_TEMPLATE.md +24 -0
- kachedb-0.1.0/.github/workflows/ci.yml +60 -0
- kachedb-0.1.0/.github/workflows/publish.yml +53 -0
- kachedb-0.1.0/.gitignore +34 -0
- kachedb-0.1.0/CHANGELOG.md +140 -0
- kachedb-0.1.0/CODE_OF_CONDUCT.md +58 -0
- kachedb-0.1.0/CONTRIBUTING.md +56 -0
- kachedb-0.1.0/LICENSE-APACHE +176 -0
- kachedb-0.1.0/LICENSE-MIT +21 -0
- kachedb-0.1.0/Makefile +50 -0
- kachedb-0.1.0/PKG-INFO +309 -0
- kachedb-0.1.0/README.md +259 -0
- kachedb-0.1.0/SECURITY.md +24 -0
- kachedb-0.1.0/docs/guides/sglang_integration_guide.md +116 -0
- kachedb-0.1.0/docs/guides/vllm_integration_guide.md +153 -0
- kachedb-0.1.0/pyproject.toml +94 -0
- kachedb-0.1.0/src/kachedb/__init__.py +86 -0
- kachedb-0.1.0/src/kachedb/_version.py +1 -0
- kachedb-0.1.0/src/kachedb/async_client.py +588 -0
- kachedb-0.1.0/src/kachedb/client.py +652 -0
- kachedb-0.1.0/src/kachedb/connection.py +191 -0
- kachedb-0.1.0/src/kachedb/descriptor.py +208 -0
- kachedb-0.1.0/src/kachedb/dma.py +141 -0
- kachedb-0.1.0/src/kachedb/exceptions.py +25 -0
- kachedb-0.1.0/src/kachedb/integrations/__init__.py +17 -0
- kachedb-0.1.0/src/kachedb/integrations/langchain.py +149 -0
- kachedb-0.1.0/src/kachedb/integrations/llamaindex.py +89 -0
- kachedb-0.1.0/src/kachedb/pipeline.py +371 -0
- kachedb-0.1.0/src/kachedb/pool.py +294 -0
- kachedb-0.1.0/src/kachedb/py.typed +0 -0
- kachedb-0.1.0/src/kachedb/quantizer.py +73 -0
- kachedb-0.1.0/src/kachedb/resp.py +252 -0
- kachedb-0.1.0/src/kachedb/semantic/__init__.py +27 -0
- kachedb-0.1.0/src/kachedb/semantic/cache.py +266 -0
- kachedb-0.1.0/src/kachedb/semantic/embedders.py +261 -0
- kachedb-0.1.0/src/kachedb/sglang/__init__.py +14 -0
- kachedb-0.1.0/src/kachedb/sglang/connector.py +187 -0
- kachedb-0.1.0/src/kachedb/sglang/radix_adapter.py +138 -0
- kachedb-0.1.0/src/kachedb/tensor.py +206 -0
- kachedb-0.1.0/src/kachedb/vllm/__init__.py +13 -0
- kachedb-0.1.0/src/kachedb/vllm/connector.py +204 -0
- kachedb-0.1.0/src/kachedb/vllm/dma.py +11 -0
- kachedb-0.1.0/src/kachedb/vllm/prefix_cache.py +111 -0
- kachedb-0.1.0/tests/__init__.py +1 -0
- kachedb-0.1.0/tests/conftest.py +123 -0
- kachedb-0.1.0/tests/test_async_client.py +31 -0
- kachedb-0.1.0/tests/test_batch_vectors.py +120 -0
- kachedb-0.1.0/tests/test_client.py +193 -0
- kachedb-0.1.0/tests/test_integration.py +120 -0
- kachedb-0.1.0/tests/test_integrations.py +144 -0
- kachedb-0.1.0/tests/test_phase3.py +157 -0
- kachedb-0.1.0/tests/test_pipeline.py +142 -0
- kachedb-0.1.0/tests/test_pool.py +37 -0
- kachedb-0.1.0/tests/test_resp.py +155 -0
- kachedb-0.1.0/tests/test_semantic_cache.py +152 -0
- kachedb-0.1.0/tests/test_semantic_standalone.py +134 -0
- kachedb-0.1.0/tests/test_sglang_connector.py +262 -0
- kachedb-0.1.0/tests/test_tensor.py +148 -0
- kachedb-0.1.0/tests/test_vllm_connector.py +149 -0
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
name: "🐛 Bug Report"
|
|
2
|
+
description: "File a bug report for kachedb-py"
|
|
3
|
+
labels: ["bug"]
|
|
4
|
+
body:
|
|
5
|
+
- type: markdown
|
|
6
|
+
attributes:
|
|
7
|
+
value: "Thanks for taking the time to report a bug in `kachedb-py`!"
|
|
8
|
+
- type: textarea
|
|
9
|
+
id: description
|
|
10
|
+
attributes:
|
|
11
|
+
label: "Describe the bug"
|
|
12
|
+
description: "A clear and concise description of what the bug is."
|
|
13
|
+
validations:
|
|
14
|
+
required: true
|
|
15
|
+
- type: textarea
|
|
16
|
+
id: reproduction
|
|
17
|
+
attributes:
|
|
18
|
+
label: "Steps to Reproduce"
|
|
19
|
+
description: "Minimal code snippet or steps to reproduce the issue."
|
|
20
|
+
placeholder: |
|
|
21
|
+
from kachedb import KacheClient
|
|
22
|
+
client = KacheClient()
|
|
23
|
+
...
|
|
24
|
+
validations:
|
|
25
|
+
required: true
|
|
26
|
+
- type: textarea
|
|
27
|
+
id: expected
|
|
28
|
+
attributes:
|
|
29
|
+
label: "Expected Behavior"
|
|
30
|
+
description: "What you expected to happen."
|
|
31
|
+
validations:
|
|
32
|
+
required: true
|
|
33
|
+
- type: input
|
|
34
|
+
id: environment
|
|
35
|
+
attributes:
|
|
36
|
+
label: "Environment"
|
|
37
|
+
description: "Python version, OS, torch/vllm versions."
|
|
38
|
+
placeholder: "Python 3.11, Ubuntu 24.04, torch 2.4.0, vLLM 0.6.0"
|
|
39
|
+
validations:
|
|
40
|
+
required: false
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
name: "🚀 Feature Request / Proposal"
|
|
2
|
+
description: "Suggest a new feature or improvement for kachedb-py"
|
|
3
|
+
labels: ["enhancement"]
|
|
4
|
+
body:
|
|
5
|
+
- type: markdown
|
|
6
|
+
attributes:
|
|
7
|
+
value: "Have an idea for `kachedb-py`? We'd love to hear it!"
|
|
8
|
+
- type: textarea
|
|
9
|
+
id: problem
|
|
10
|
+
attributes:
|
|
11
|
+
label: "Problem or Use Case"
|
|
12
|
+
description: "Is your feature request related to a problem or a specific LLM framework?"
|
|
13
|
+
validations:
|
|
14
|
+
required: true
|
|
15
|
+
- type: textarea
|
|
16
|
+
id: proposal
|
|
17
|
+
attributes:
|
|
18
|
+
label: "Proposed Solution"
|
|
19
|
+
description: "A clear and concise description of what you want to happen."
|
|
20
|
+
validations:
|
|
21
|
+
required: true
|
|
22
|
+
- type: textarea
|
|
23
|
+
id: alternatives
|
|
24
|
+
attributes:
|
|
25
|
+
label: "Alternative Solutions"
|
|
26
|
+
description: "Any alternative solutions or features you've considered."
|
|
27
|
+
validations:
|
|
28
|
+
required: false
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
## 📋 Description
|
|
2
|
+
|
|
3
|
+
Provide a brief summary of the changes introduced by this Pull Request.
|
|
4
|
+
|
|
5
|
+
- What problem does this solve?
|
|
6
|
+
- What is the new behavior?
|
|
7
|
+
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
## 🧪 Testing Checklist
|
|
11
|
+
|
|
12
|
+
- [ ] All unit tests pass: `pytest tests/ -v --ignore=tests/test_integration.py`
|
|
13
|
+
- [ ] Integration tests pass (if applicable): `pytest tests/test_integration.py -v`
|
|
14
|
+
- [ ] Linter checks pass: `ruff check src/ tests/`
|
|
15
|
+
- [ ] Code formatting verified: `ruff format --check src/ tests/`
|
|
16
|
+
- [ ] Type check passes: `mypy src/kachedb/`
|
|
17
|
+
- [ ] Documentation / `README.md` updated (if applicable)
|
|
18
|
+
- [ ] `CHANGELOG.md` updated
|
|
19
|
+
|
|
20
|
+
---
|
|
21
|
+
|
|
22
|
+
## 🔗 Related Issues / PRs
|
|
23
|
+
|
|
24
|
+
Closes # (issue number)
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
name: CI
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
push:
|
|
5
|
+
branches: [main]
|
|
6
|
+
pull_request:
|
|
7
|
+
branches: [main]
|
|
8
|
+
|
|
9
|
+
concurrency:
|
|
10
|
+
group: ci-${{ github.ref }}
|
|
11
|
+
cancel-in-progress: true
|
|
12
|
+
|
|
13
|
+
env:
|
|
14
|
+
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
|
|
15
|
+
|
|
16
|
+
jobs:
|
|
17
|
+
lint:
|
|
18
|
+
name: Lint
|
|
19
|
+
runs-on: ubuntu-latest
|
|
20
|
+
steps:
|
|
21
|
+
- uses: actions/checkout@v4
|
|
22
|
+
|
|
23
|
+
- name: Set up Python
|
|
24
|
+
uses: actions/setup-python@v5
|
|
25
|
+
with:
|
|
26
|
+
python-version: "3.12"
|
|
27
|
+
|
|
28
|
+
- name: Install dependencies
|
|
29
|
+
run: pip install -e ".[dev,torch]"
|
|
30
|
+
|
|
31
|
+
- name: Ruff check
|
|
32
|
+
run: ruff check src/ tests/
|
|
33
|
+
|
|
34
|
+
- name: Ruff format check
|
|
35
|
+
run: ruff format --check src/ tests/
|
|
36
|
+
|
|
37
|
+
- name: Mypy type check
|
|
38
|
+
run: mypy src/kachedb/
|
|
39
|
+
|
|
40
|
+
test:
|
|
41
|
+
name: Test (Python ${{ matrix.python-version }})
|
|
42
|
+
runs-on: ubuntu-latest
|
|
43
|
+
strategy:
|
|
44
|
+
fail-fast: false
|
|
45
|
+
matrix:
|
|
46
|
+
python-version: ["3.10", "3.11", "3.12", "3.13"]
|
|
47
|
+
|
|
48
|
+
steps:
|
|
49
|
+
- uses: actions/checkout@v4
|
|
50
|
+
|
|
51
|
+
- name: Set up Python ${{ matrix.python-version }}
|
|
52
|
+
uses: actions/setup-python@v5
|
|
53
|
+
with:
|
|
54
|
+
python-version: ${{ matrix.python-version }}
|
|
55
|
+
|
|
56
|
+
- name: Install package with dev dependencies
|
|
57
|
+
run: pip install -e ".[dev,torch]"
|
|
58
|
+
|
|
59
|
+
- name: Run unit tests
|
|
60
|
+
run: pytest tests/ -v --ignore=tests/test_integration.py -m "not integration" -x
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
name: Publish to PyPI
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
release:
|
|
5
|
+
types: [published]
|
|
6
|
+
|
|
7
|
+
permissions:
|
|
8
|
+
id-token: write # Required for Trusted Publisher (OIDC)
|
|
9
|
+
|
|
10
|
+
env:
|
|
11
|
+
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
|
|
12
|
+
|
|
13
|
+
jobs:
|
|
14
|
+
build:
|
|
15
|
+
name: Build Distribution
|
|
16
|
+
runs-on: ubuntu-latest
|
|
17
|
+
steps:
|
|
18
|
+
- uses: actions/checkout@v4
|
|
19
|
+
|
|
20
|
+
- name: Set up Python
|
|
21
|
+
uses: actions/setup-python@v5
|
|
22
|
+
with:
|
|
23
|
+
python-version: "3.12"
|
|
24
|
+
|
|
25
|
+
- name: Install build tools
|
|
26
|
+
run: pip install build
|
|
27
|
+
|
|
28
|
+
- name: Build sdist and wheel
|
|
29
|
+
run: python -m build
|
|
30
|
+
|
|
31
|
+
- name: Upload distribution artifacts
|
|
32
|
+
uses: actions/upload-artifact@v4
|
|
33
|
+
with:
|
|
34
|
+
name: dist
|
|
35
|
+
path: dist/
|
|
36
|
+
|
|
37
|
+
publish:
|
|
38
|
+
name: Publish to PyPI
|
|
39
|
+
needs: build
|
|
40
|
+
runs-on: ubuntu-latest
|
|
41
|
+
environment:
|
|
42
|
+
name: pypi
|
|
43
|
+
url: https://pypi.org/project/kachedb/
|
|
44
|
+
|
|
45
|
+
steps:
|
|
46
|
+
- name: Download distribution artifacts
|
|
47
|
+
uses: actions/download-artifact@v4
|
|
48
|
+
with:
|
|
49
|
+
name: dist
|
|
50
|
+
path: dist/
|
|
51
|
+
|
|
52
|
+
- name: Publish to PyPI
|
|
53
|
+
uses: pypa/gh-action-pypi-publish@release/v1
|
kachedb-0.1.0/.gitignore
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
# Python
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*$py.class
|
|
5
|
+
*.so
|
|
6
|
+
*.egg-info/
|
|
7
|
+
*.egg
|
|
8
|
+
dist/
|
|
9
|
+
build/
|
|
10
|
+
.eggs/
|
|
11
|
+
|
|
12
|
+
# Virtual environments
|
|
13
|
+
.venv
|
|
14
|
+
.venv/
|
|
15
|
+
venv/
|
|
16
|
+
env/
|
|
17
|
+
|
|
18
|
+
# IDE
|
|
19
|
+
.idea/
|
|
20
|
+
.vscode/
|
|
21
|
+
*.swp
|
|
22
|
+
*.swo
|
|
23
|
+
|
|
24
|
+
# Testing
|
|
25
|
+
.pytest_cache/
|
|
26
|
+
.mypy_cache/
|
|
27
|
+
.ruff_cache/
|
|
28
|
+
htmlcov/
|
|
29
|
+
.coverage
|
|
30
|
+
coverage.xml
|
|
31
|
+
|
|
32
|
+
# OS
|
|
33
|
+
.DS_Store
|
|
34
|
+
Thumbs.db
|
|
@@ -0,0 +1,140 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
All notable changes to the `kachedb` Python SDK will be documented in this file.
|
|
4
|
+
|
|
5
|
+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
6
|
+
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
|
+
|
|
8
|
+
## [0.1.0] — 2026-09-09
|
|
9
|
+
|
|
10
|
+
### Added
|
|
11
|
+
- **Redis Admin & Keyspace Introspection Primitives (`KacheClient`, `AsyncKacheClient`, `Pipeline`, `AsyncPipeline`):**
|
|
12
|
+
- Added `dbsize()`: returns the total number of keys stored in the database.
|
|
13
|
+
- Added `type(key)`: returns the data type of the key (`"string"`, `"vector"`, or `"none"`).
|
|
14
|
+
- Added `flushdb()` and `flushall()`: clears in-memory keyspace and returns `True`.
|
|
15
|
+
- **Server Parity & Compatibility:**
|
|
16
|
+
- 100% feature parity with KacheDB Server `v0.1.0` production release.
|
|
17
|
+
- Aligned documentation links with the official docs site at `https://vubon.github.io/kachedb/`.
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## [0.1.0b3] — 2026-09-06
|
|
22
|
+
|
|
23
|
+
### Added
|
|
24
|
+
- **Phase 3 SQ8 Vector Quantization (`kachedb.vector` & `kachedb.semantic`):**
|
|
25
|
+
- Added support for 8-bit Scalar Quantization (SQ8) compressing vector embeddings with 75% memory footprint reduction.
|
|
26
|
+
- Client APIs and semantic caching pipelines seamlessly handle quantized vector queries.
|
|
27
|
+
- **HNSW Vector Indexing Commands:**
|
|
28
|
+
- Added `vindex_create` support for Hierarchical Navigable Small World (`hnsw`) index type with configurable `m` and `ef_construction` parameters.
|
|
29
|
+
- **TLS 1.3 Transport Security & Mutual TLS (`kachedb.ConnectionPool`):**
|
|
30
|
+
- Added native TLS 1.3 encryption across synchronous and asynchronous connection pools (`ssl=True`).
|
|
31
|
+
- Added support for CA certificates (`ssl_ca_certs`), client certificate chains (`ssl_certfile`, `ssl_keyfile`), and hostname verification (`ssl_check_hostname`).
|
|
32
|
+
- **AOF & Administrative Commands:**
|
|
33
|
+
- Added `bgrewriteaof()` command triggering online AOF journal compaction.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## [0.1.0b2] — 2026-09-03
|
|
38
|
+
|
|
39
|
+
### Added
|
|
40
|
+
- **Batch Vector Operations (`KacheClient` & `AsyncKacheClient`):**
|
|
41
|
+
- Added `vadd_batch(index, items)` for bulk ingestion of vector embeddings and payloads in a single network round-trip.
|
|
42
|
+
- Added `vsearch_batch(index, query_vectors, top_k, threshold)` for multi-query simultaneous vector nearest-neighbor search.
|
|
43
|
+
- **AI Ecosystem Integrations (`kachedb.integrations`):**
|
|
44
|
+
- **LangChain:** `KacheDBCache` (exact-match prompt caching) and `KacheDBSemanticCache` (SIMD vector similarity matching).
|
|
45
|
+
- **LlamaIndex:** `KacheDBKVStore` (key-value storage) and `KacheDBIndexStore` (index metadata storage).
|
|
46
|
+
- **Type Checking & Embedder Robustness:**
|
|
47
|
+
- Dynamic type-safe fallback imports across `fastembed`, `sentence-transformers`, `openai`, and `vllm`.
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## [0.1.0b1] — 2026-08-30
|
|
52
|
+
|
|
53
|
+
### Added
|
|
54
|
+
- **Complete Redis TTL Lifecycle (`kachedb.KacheClient` & `kachedb.AsyncKacheClient`):**
|
|
55
|
+
- Added `expire`, `pexpire`, `expireat`, `pexpireat`, `ttl`, `pttl`, and `persist`.
|
|
56
|
+
- **Extended Redis Command Primitives:**
|
|
57
|
+
- Added atomic operations: `mset`, `incr`, `decr`, `incrby`, `decrby`, `append`, `strlen`, and `info`.
|
|
58
|
+
- **Async Vector & Semantic Operations (`AsyncKacheClient`):**
|
|
59
|
+
- Added asynchronous vector search and index operations: `vadd`, `vsearch`, `vdel`, and `vstats`.
|
|
60
|
+
- **Asynchronous Semantic Cache (`kachedb.semantic.AsyncSemanticCache`):**
|
|
61
|
+
- Added high-level async intent matching and LLM response caching engine.
|
|
62
|
+
- **Full Pipeline Support (`Pipeline` & `AsyncPipeline`):**
|
|
63
|
+
- Added support for all extended Redis primitives and TTL lifecycle commands in batch pipelines.
|
|
64
|
+
|
|
65
|
+
---
|
|
66
|
+
|
|
67
|
+
## [0.1.0a5] — 2026-08-28
|
|
68
|
+
|
|
69
|
+
### Added
|
|
70
|
+
- **In-Memory Semantic Cache Engine (`kachedb.semantic`):**
|
|
71
|
+
- Added `SemanticCache` class for intent-based LLM query caching matching by cosine similarity ($< 50\ \mu\text{s}$ cache resolution) with automatic TTL eviction and threshold tuning.
|
|
72
|
+
- Added `SearchResult` data class encapsulating matched key, similarity score, and cached response payload.
|
|
73
|
+
- **Pluggable Embedding Providers (`kachedb.semantic.embedders`):**
|
|
74
|
+
- `TransformersEmbedder`: Native HuggingFace `AutoModel` with mean pooling over token embeddings.
|
|
75
|
+
- `FastEmbedAdapter`: Lightweight ONNX Runtime embedding generator via `fastembed`.
|
|
76
|
+
- `SentenceTransformersAdapter`: HuggingFace `SentenceTransformer` adapter.
|
|
77
|
+
- `OpenAIAdapter`: Remote embedding integration with OpenAI (`text-embedding-3-small`).
|
|
78
|
+
- `CallableAdapter`: Wrapper for any custom user embedding function (`Callable[[str], list[float]]`).
|
|
79
|
+
- `MockEmbedder`: Deterministic, zero-dependency token and semantic-cluster pseudo-embedder for local tests and simulations.
|
|
80
|
+
- **Native Vector Client Operations (`kachedb.KacheClient`):**
|
|
81
|
+
- `client.vadd(index, item_id, vector, payload, ex)`: Store vector embedding with optional metadata and TTL.
|
|
82
|
+
- `client.vsearch(index, query_vector, top_k, threshold)`: Nearest-neighbor search returning `[(item_id, similarity, payload), ...]`.
|
|
83
|
+
- `client.vdel(index, item_id)`: Remove vector from named index.
|
|
84
|
+
- `client.vstats(index)`: Retrieve index dimension, active vector count, and RAM footprint.
|
|
85
|
+
- **Test Suite & Type Checking:** Added `tests/test_semantic_cache.py` and `tests/test_semantic_standalone.py` with full type annotations, mypy compliance, and ruff formatting (102/102 tests passing).
|
|
86
|
+
|
|
87
|
+
---
|
|
88
|
+
|
|
89
|
+
## [0.1.0a4] — 2026-08-26
|
|
90
|
+
|
|
91
|
+
### Added
|
|
92
|
+
- **SGLang (RadixAttention) KV-Cache Connector (`kachedb.sglang`):**
|
|
93
|
+
- Added `KacheDBSGLangConnector` for microsecond-tier tree node offloading and prefix restoration via POSIX Shared Memory (`/dev/shm`).
|
|
94
|
+
- Added `KacheDBRadixAdapter` with chained Blake2b hashing for variable-length token slices ($H_k = \text{Blake2b}(H_{\text{parent}} \,\|\, \text{len} \,\|\, \text{tokens})$).
|
|
95
|
+
- Added `RadixNodeDescriptor` for tracking tree node IDs, layer offsets, parent hashes, and metadata.
|
|
96
|
+
- **Universal Multi-Precision DMA (`kachedb.dma` & `TensorCodec`):**
|
|
97
|
+
- Added `TensorCodec` in `kachedb.descriptor` with dynamic registry mapping for `torch.bfloat16` (BF16), `torch.float16` (FP16), `torch.float32` (FP32), and `torch.int8` (INT8).
|
|
98
|
+
- Refactored `KacheDBMemoryManager` into top-level `kachedb.dma`, universally shared across `kachedb.vllm` and `kachedb.sglang` with 100% backward compatibility.
|
|
99
|
+
- **Production Integration Guides:**
|
|
100
|
+
- Added `docs/guides/vllm_integration_guide.md` with multi-GPU CLI flags, programmatic loops, and production `docker-compose.yml`.
|
|
101
|
+
- Added `docs/guides/sglang_integration_guide.md` with RadixAttention tree-branching and multi-precision configurations.
|
|
102
|
+
- **Unit Test Suite:** Added `tests/test_sglang_connector.py` covering variable-length hashing, single/multi-node offloads, branching tree resolution, and multi-precision FP16/BF16/FP32/INT8 bit-exact roundtrips (85/85 tests passing).
|
|
103
|
+
- **Packaging:** Added `sglang = ["torch>=2.0", "sglang>=0.3.0"]` extra to `pyproject.toml`.
|
|
104
|
+
|
|
105
|
+
---
|
|
106
|
+
|
|
107
|
+
## [0.1.0a3] — 2026-08-25
|
|
108
|
+
|
|
109
|
+
### Added
|
|
110
|
+
- **vLLM Distributed KV-Transfer Connector (`kachedb.vllm`):**
|
|
111
|
+
- Added `KacheDBConnector` subclassing vLLM's `KVConnectorBase` for zero-copy PagedAttention block offloading and restoration.
|
|
112
|
+
- Added `KacheDBPrefixCache` for 64-bit deterministic chained token chunk hashing ($H_k = \text{hash}(H_{k-1} + \text{tokens})$).
|
|
113
|
+
- Added `KacheDBMemoryManager` for microsecond-tier PagedAttention block swapping via POSIX Shared Memory (`/dev/shm`).
|
|
114
|
+
- **Unit Test Suite:** Added `tests/test_vllm_connector.py` covering block hash determinism, hash chaining, longest prefix search, and multi-layer PagedAttention tensor restoration (76/76 tests passing).
|
|
115
|
+
- **Packaging Dependencies:** Added `vllm = ["torch>=2.0", "vllm>=0.6.0"]` and `all = [...]` optional extras in `pyproject.toml`.
|
|
116
|
+
- **Documentation:** Added vLLM CLI launch guide (`vllm serve ... --kv-transfer-config`) and programmatic connector usage in `README.md`.
|
|
117
|
+
|
|
118
|
+
---
|
|
119
|
+
|
|
120
|
+
## [0.1.0a2] — 2026-08-25
|
|
121
|
+
|
|
122
|
+
### Added
|
|
123
|
+
- **TensorBlockDescriptor Serialization:**
|
|
124
|
+
- Added `.to_bytes()` method to serialize 64-byte C-ABI descriptor headers to binary buffers.
|
|
125
|
+
- **LLM Precision Support:**
|
|
126
|
+
- Expanded `TensorDType` enum to cover `FP32`, `FP16`, `BF16` (bfloat16), `FP8E4M3`, `FP8E5M2`, `INT8`, and `INT4` precisions.
|
|
127
|
+
|
|
128
|
+
---
|
|
129
|
+
|
|
130
|
+
## [0.1.0a1] — 2026-08-23
|
|
131
|
+
|
|
132
|
+
### Added
|
|
133
|
+
- **Initial Alpha Release of `kachedb` Python SDK:**
|
|
134
|
+
- Synchronous `KacheClient` supporting `PING`, `GET`, `SET` (with `EX`/`PX` TTL), `MGET`, `DEL`, and `EXISTS`.
|
|
135
|
+
- Asynchronous `AsyncKacheClient` with non-blocking `asyncio` networking.
|
|
136
|
+
- Thread-safe `ConnectionPool` and `AsyncConnectionPool` with automatic health checks.
|
|
137
|
+
- `Pipeline` and `AsyncPipeline` for batching multiple commands in a single TCP round-trip.
|
|
138
|
+
- Zero-allocation RESP2/RESP3 streaming protocol reader (`RespReader` and `AsyncRespReader`).
|
|
139
|
+
- Zero-copy tensor memory mapping utilities (`attach_shm`, `read_tensor`, `read_torch_tensor`) via Linux `/dev/shm`.
|
|
140
|
+
- Full PEP 561 type safety annotations with `py.typed` marker.
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
|
2
|
+
|
|
3
|
+
## Our Pledge
|
|
4
|
+
|
|
5
|
+
We as members, contributors, and leaders pledge to make participation in our
|
|
6
|
+
community a harassment-free experience for everyone, regardless of age, body
|
|
7
|
+
size, visible or invisible disability, ethnicity, sex characteristics, gender
|
|
8
|
+
identity and expression, level of experience, education, socio-economic status,
|
|
9
|
+
nationality, personal appearance, race, caste, color, religion, or sexual
|
|
10
|
+
identity and orientation.
|
|
11
|
+
|
|
12
|
+
We pledge to act and interact in ways that contribute to an open, welcoming,
|
|
13
|
+
diverse, inclusive, and healthy community.
|
|
14
|
+
|
|
15
|
+
## Our Standards
|
|
16
|
+
|
|
17
|
+
Examples of behavior that contributes to a positive environment for our
|
|
18
|
+
community include:
|
|
19
|
+
|
|
20
|
+
* Demonstrating empathy and kindness toward other people
|
|
21
|
+
* Being respectful of differing opinions, viewpoints, and experiences
|
|
22
|
+
* Giving and gracefully accepting constructive feedback
|
|
23
|
+
* Accepting responsibility and apologizing to those affected by our mistakes,
|
|
24
|
+
and learning from the experience
|
|
25
|
+
* Focusing on what is best not just for us as individuals, but for the
|
|
26
|
+
overall community
|
|
27
|
+
|
|
28
|
+
Examples of unacceptable behavior include:
|
|
29
|
+
|
|
30
|
+
* The use of sexualized language or imagery, and sexual attention or advances of
|
|
31
|
+
any kind
|
|
32
|
+
* Trolling, insulting or derogatory comments, and personal or political attacks
|
|
33
|
+
* Public or private harassment
|
|
34
|
+
* Publishing others' private information, such as a physical or email
|
|
35
|
+
address, without their explicit permission
|
|
36
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
|
37
|
+
professional setting
|
|
38
|
+
|
|
39
|
+
## Enforcement Responsibilities
|
|
40
|
+
|
|
41
|
+
Community leaders are responsible for clarifying and enforcing our standards of
|
|
42
|
+
acceptable behavior and will take appropriate and fair corrective action in
|
|
43
|
+
response to any behavior that they deem inappropriate, threatening, offensive,
|
|
44
|
+
or harmful.
|
|
45
|
+
|
|
46
|
+
## Scope
|
|
47
|
+
|
|
48
|
+
This Code of Conduct applies within all community spaces, and also applies when
|
|
49
|
+
an individual is officially representing the community in public spaces.
|
|
50
|
+
|
|
51
|
+
## Attribution
|
|
52
|
+
|
|
53
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
|
54
|
+
version 2.1, available at
|
|
55
|
+
[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
|
|
56
|
+
|
|
57
|
+
[homepage]: https://www.contributor-covenant.org
|
|
58
|
+
[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
# Contributing to KacheDB Python SDK
|
|
2
|
+
|
|
3
|
+
Thank you for your interest in contributing to `kachedb-py`! We welcome contributions from the community.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## 🛠️ Development Setup
|
|
8
|
+
|
|
9
|
+
### 1. Clone & Environment
|
|
10
|
+
```bash
|
|
11
|
+
git clone https://github.com/vubon/kachedb-py.git
|
|
12
|
+
cd kachedb-py
|
|
13
|
+
|
|
14
|
+
# Create a virtual environment
|
|
15
|
+
python3 -m venv .venv
|
|
16
|
+
source .venv/bin/activate
|
|
17
|
+
|
|
18
|
+
# Install in editable mode with dev dependencies
|
|
19
|
+
pip install -e ".[dev,torch,vllm]"
|
|
20
|
+
```
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 🧪 Testing & Code Quality
|
|
25
|
+
|
|
26
|
+
Before submitting a Pull Request, make sure all tests, linter checks, and type checks pass:
|
|
27
|
+
|
|
28
|
+
### 1. Run Unit Tests
|
|
29
|
+
```bash
|
|
30
|
+
pytest tests/ -v --ignore=tests/test_integration.py
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
### 2. Run Integration Tests (Requires running KacheDB server on 127.0.0.1:6379)
|
|
34
|
+
```bash
|
|
35
|
+
pytest tests/test_integration.py -v
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
### 3. Linting & Formatting
|
|
39
|
+
```bash
|
|
40
|
+
ruff check src/ tests/
|
|
41
|
+
ruff format --check src/ tests/
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### 4. Type Checking
|
|
45
|
+
```bash
|
|
46
|
+
mypy src/kachedb/
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## 📦 Pull Request Guidelines
|
|
52
|
+
|
|
53
|
+
1. **Create a branch:** Use descriptive branch names (e.g. `feat/paged-attention-stream`, `fix/async-pool-timeout`).
|
|
54
|
+
2. **Write tests:** Every new feature or bug fix must include corresponding tests in `tests/`.
|
|
55
|
+
3. **Update CHANGELOG.md:** Add your change under the `[Unreleased]` or current alpha release section.
|
|
56
|
+
4. **Follow Semantic Versioning:** Breaking changes require explicit RFC discussion in GitHub Issues.
|
|
@@ -0,0 +1,176 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|