Skip to main content

EngramDB 的 Python 分发包

Disk-first storage engine for Engram / PLE n-gram memory tables (Rust).

分发名 engramdb-python(PyPI 相似名规避);import 名仍为 engramdb。

当前 v0.2.9 同时包含两条 Python 接入路径:

  1. PyO3 原生扩展(优先):crates/engramdb-pyo3,构建后以 python/engramdb/_engramdb.so 提供 Store / View / PageReader / Linux IoUringPageReader。
  2. ctypes C-ABI 回退:crates/engramdb-python,无 PyO3 构建产物时也能用。

python/engramdb/__init__.py 会自动优先加载 PyO3,失败则回退 ctypes。

安装

已发布到 PyPI,包名 engramdb-python,import 名 engramdb:

# 直接安装发布版
python3 -m pip install --upgrade engramdb-python

# 或使用 uv
uv add engramdb-python

开发/本地构建也可以使用:

# 方式 1:maturin 构建 wheel(推荐,直接产生可安装的 native wheel)
cd python
CARGO_HOME=/tmp/cargo-home RUSTFLAGS="-C link-arg=-undefined -C link-arg=dynamic_lookup" \
  maturin build --release --interpreter python3

# 方式 2:开发期内直接构建并复制到包目录
CARGO_HOME=/tmp/cargo-home RUSTFLAGS="-C link-arg=-undefined -C link-arg=dynamic_lookup" \
  cargo build -p engramdb-pyo3 --release
cp target/release/lib_engramdb.dylib python/engramdb/_engramdb.so

# 在 engram-peft 等项目中用 uv 添加本地开发依赖
cd ~/code/engram-peft
uv add --editable ../EngramDB/python

快速使用

存储 / 视图 / 页读取

import engramdb

# 打开 Store-I:目录内为 shard_000.bin 等定长行文件
store = engramdb.Store("path/to/rows", shards=1, rows_per_shard=100, width=256)
row_bytes = store.fetch([0, 1, 2])   # bytes, 每条 256B
store.close()

# 打开 Store-P 视图
view = engramdb.View("path/to/view.bin")
rec = view.read_record(0)            # 一条 e_t 记录

# SGLang 兼容:从多个 fd/offset 读页(Unix 有 PageReader,Linux 另有 IoUringPageReader)
reader = engramdb.PageReader(page_size=4096)
pages = reader.read_pages([fd0, fd1], [offset0, offset1])

PLE rowid、自动发现、FP8 scale

from engramdb import rowids_for_seq, discover_ple, load_ple_weight_scale, load_ple_multipliers

# Qwen PLE / Engram 确定性 rowid:[T, 16]
rows = rowids_for_seq([248044, 1000, 99999, 42])

# 从 checkpoint 自动发现 PLE 表元数据、weight_scale 与 rowid multipliers
info = discover_ple("/path/to/Qwen3.8-Flash-Next")
scale = load_ple_weight_scale("/path/to/Qwen3.8-Flash-Next")
mult = load_ple_multipliers("/path/to/Qwen3.8-Flash-Next")

# discovery 返回的 info 已包含 weight_scale 和 multipliers,可直接用于 rowids
rows = rowids_for_seq([248044, 1000, 99999, 42], info=info)

真实 PLE 磁盘 Adapter

from engramdb import Store
from engramdb.ple_adapter import disk_ple_from_discovery

info = discover_ple("/path/to/Qwen3.8-Flash-Next")
store = Store("/path/to/real-ple-rows", shards=128, rows_per_shard=2_500_012, width=160)
ple = disk_ple_from_discovery(store, info)  # 自动使用 weight_scale

引擎适配层

目标是 不改 vLLM / SGLang 源码,启动前执行一小段 hook 即可把 PLE 表切到 EngramDB。

vLLM

from engramdb import Store
from engramdb.vllm_plugin import install_vllm_ple

store = Store("/path/to/engram-rows", shards=..., rows_per_shard=..., width=...)

install_vllm_ple(
    Qwen3_8FlashNextNGramEmbedding,   # 实际运行的 vLLM 模型类
    store=store,
    attr_name="embed_tokens_per_layer",
    embedding_dim=hidden_size_per_layer_input,
)

from vllm import LLM
llm = LLM(model="...", ...)

如果已经构造好模型实例,可以用:

from engramdb.vllm_plugin import patch_named_embedding
patch_named_embedding(model, "embed_tokens_per_layer", store=store, embedding_dim=...)

SGLang

from engramdb.sglang import install_sglang_ple

install_sglang_ple(
    Gemma4Model,                      # 实际运行的 SGLang 模型类
    store=store,
    attr_name="embed_tokens_per_layer",
    embedding_dim=hidden_size_per_layer_input,
)

低层 reader 替换:

from engramdb.sglang import install_sglang_io_uring_reader
install_sglang_io_uring_reader()

engram-peft 集成

安装 engramdb-python 后,可以直接使用内置的磁盘版 MultiHeadEmbedding:

import engramdb
from engramdb.integrations import install_disk_multi_head_embedding

store = engramdb.Store("path/to/embedding-store", shards=1, rows_per_shard=100, width=256)
install_disk_multi_head_embedding(store)

# 之后再调用 engram-peft 的 get_engram_model(...) 即可让 Engram 层从磁盘读取 embedding

真实 Qwen PLE FP8 Store 使用专用注入:

from engramdb.integrations import install_real_qwen_ple_embedding

# scale 会从 checkpoint 自动读取;也可以显式传 scale=0.0002
install_real_qwen_ple_embedding(
    store,
    model_dir="/path/to/Qwen3.8-Flash-Next",
)

多表 / Arrow / 最小服务原型

多表按目录组织:

from engramdb import Database

db = Database("path/to/tables-root")
print(db.list_tables())  # ["alpha", "beta"]

raw = db.fetch("alpha", [1, 3], shards=1, rows_per_shard=100, width=256)

可选 Arrow 读取(需要 pyarrow):

from engramdb.arrow_utils import store_fetch_arrow, table_to_ipc_bytes

table = store_fetch_arrow(store, [0, 1, 2])
ipc = table_to_ipc_bytes(table)   # Arrow IPC stream bytes

最小服务(当前为原型,提供两种 wire 模式):

JSON 模式:

from engramdb import Database
from engramdb.server import EngramDBServer

server = EngramDBServer(Database("path/to/tables-root"), host="127.0.0.1", port=8765)
server.serve_forever()

二进制模式(长度前缀 + 1-byte kind,fetch_raw 直接返回原始字节, fetch_arrow 直接返回 Arrow IPC stream,不需要 base64 包装):

from engramdb import Database, EngramDBBinaryServer, EngramDBClient

server = EngramDBBinaryServer(
    Database("path/to/tables-root"),
    host="127.0.0.1",
    port=8765,
)
server.serve_forever()

# 客户端
with EngramDBClient("127.0.0.1", 8765) as client:
    tables = client.list_tables()
    raw = client.fetch_raw("alpha", [0, 1, 2], shards=1, rows_per_shard=100, width=256)
    ipc = client.fetch_arrow("alpha", [0, 1, 2], shards=1, rows_per_shard=100, width=256)

服务命令包括:

  • ping
  • list_tables
  • fetch / fetch_raw
  • fetch_arrow(JSON 模式返回 base64 封装的 Arrow IPC;二进制模式返回裸 Arrow IPC stream)
  • view_read

注意:PyO3 Store 是不可跨线程共享的 unsendable 对象,因此服务端 Database.fetch 会在每个请求所在线程新开 Store;多线程共享连接的后端需要 Rust 侧安全句柄或线程池。

定位(一句话)

让"确定性哈希的 n-gram 记忆表"(Qwen PLE、DeepSeek Engram 等)像数据库一样落盘、建索引、预取、服务化——单机 CPU+NVMe 低延迟推理 / 高吞吐训练预处理。

详细文档见上游仓库 docs/(design.md / specifications / roadmap)以及 examples/interop_engram_peft.py。

Metadata

Release files for engramdb-python 0.2.9

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for engramdb-python 0.2.9
File Size Uploaded
engramdb_python-0.2.9.tar.gz 57.2 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for engramdb-python 0.2.9
File
engramdb_python-0.2.9-cp310-abi3-win_amd64.whl CPython 3.10 abi3 Windows x86-64 Details
engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl CPython 3.10 abi3 Linux glibc 2.17+ x86-64 Details
engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl CPython 3.10 abi3 Linux glibc 2.17+ ARM64 Details
engramdb_python-0.2.9-cp310-abi3-macosx_11_0_arm64.whl CPython 3.10 abi3 macOS 11.0+ ARM64 Details
engramdb_python-0.2.9-cp310-abi3-macosx_10_12_x86_64.whl CPython 3.10 abi3 macOS 10.12+ x86-64 Details

Total release size: 1.7 MB

Release files / engramdb_python-0.2.9.tar.gz

Download URL engramdb_python-0.2.9.tar.gz
Size 57.2 kB
Tags Source
SHA-256 checksum
How to use checksums
3d5b7e5f6d17cb930b33b4be1f5ddd68494f9956f263bd7a54e7a1efa1d5f435
BLAKE2b-256 checksum
How to use checksums
c94b0b0be7a57ce54d8202e7e48004de562f70344cac2222a641d9e8dbb15365
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release files / engramdb_python-0.2.9-cp310-abi3-win_amd64.whl

Download URL engramdb_python-0.2.9-cp310-abi3-win_amd64.whl
Size 238.8 kB
Tags CPython 3.10 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
55c54b1f0fdf2e7d982ab6b38472296b5ba9749f03028a66c5068bf7311a7b59
BLAKE2b-256 checksum
How to use checksums
f04f40199d19dae94ecdfaa3b8afac229457fa08e6dedc54409a4908d5801ce8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release files / engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 363.9 kB
Tags CPython 3.10 Linux glibc 2.17+ x86-64 abi3
SHA-256 checksum
How to use checksums
298d11045b6ea75f3ad2924092fe1f5a8e2e9c32ae8fa902be899ac834dbefca
BLAKE2b-256 checksum
How to use checksums
50336ac47880b52f9f9b877c9c9caa5013d425e29fd3274073d455c0c5f2e940
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release files / engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL engramdb_python-0.2.9-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 347.5 kB
Tags CPython 3.10 Linux glibc 2.17+ ARM64 abi3
SHA-256 checksum
How to use checksums
ac49e2213ad9726282e8c54d3be5c7ecd22a1814f972734292fc06f9bb4c0b60
BLAKE2b-256 checksum
How to use checksums
111e4172e096e80d0996b7a71aedbe23bc9f2d74c3aa109992092509ccd4ce9a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release files / engramdb_python-0.2.9-cp310-abi3-macosx_11_0_arm64.whl

Download URL engramdb_python-0.2.9-cp310-abi3-macosx_11_0_arm64.whl
Size 345.0 kB
Tags CPython 3.10 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
e4ac40592cebd5e343da9c783e5c0689879f531f089ddf39de315fffa951acc8
BLAKE2b-256 checksum
How to use checksums
a5bb67e87deb0d12f5fb7331f50d0a679749e82519f325d58b6f1ff2b427363a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release files / engramdb_python-0.2.9-cp310-abi3-macosx_10_12_x86_64.whl

Download URL engramdb_python-0.2.9-cp310-abi3-macosx_10_12_x86_64.whl
Size 353.8 kB
Tags CPython 3.10 abi3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
4d6bd09d39f2e629314532159c971be6fd033db508974daa421a4fc7e094cbba
BLAKE2b-256 checksum
How to use checksums
b1226f34fe38a51fdd5cbf162936010c37adc6523c75bf6c7667bf420339caa5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 31, 2026.

Transparency log

Release history Release notifications | RSS feed

0.3.0

6 release files

0.2.10

6 release files

This release

0.2.9 This release

6 release files

0.2.8

6 release files

0.2.6

6 release files

0.2.5

6 release files

0.2.4

6 release files

0.2.3

6 release files

0.2.2

6 release files

0.2.1

6 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page