osobhandClaude Opus 5.5
dce5559ff2
Every undated or pre-September section re-run on one machine on one day
(tank, AMD Ryzen 7 7800X3D, 2026-09-24, commit 5c8323c), 24 commands run
serially with the load average checked before each, with the command
recorded for each section. A separate check traced every changed number
back to the raw output; its corrections are applied (e.g. the on-disk
~820 B/record is float16 plus always-deflated text on a synthetic corpus
of 40 distinct texts, not float16 alone).
Two apparent regressions were isolated rather than published:
- knowledge-graph traversal: a real bug, fixed in the previous commit;
- the write path: v2.3.0 built and run on the same machine measures the
same as today, so the old 18 us / 6.17 ms figures (undated, other
hardware) are not reproducible; float16 adds ~2 us per save and the
int8 index nothing (both isolated by switching the bench's config).
Also:
- new multimodal_bench: cross-modal search at 1K/10K records, which the
README claimed but nothing measured;
- footprint_bench reports whether it built float16 or f32 stores and
takes --f32 (it kept printing "f32" after the default changed);
- README: performance tables, the "Why" table figures and the SQLite
migration section (from the previous migrate commit);
- CHANGELOG for this branch.
Not re-run: consolidation_efficiency's 100K row and its memory-reduction
part (stopped for time), and cross_platform.sh.
Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
73 lines
2.7 KiB
TOML
73 lines
2.7 KiB
TOML
[package]
|
|
name = "clawhdf5-agent"
|
|
version = "2.7.0"
|
|
edition = "2024"
|
|
rust-version.workspace = true
|
|
description = "HDF5-backed persistent memory store for on-device AI agents"
|
|
license = "MIT"
|
|
repository = "https://git.redclaw.dev/quantumclaw/clawhdf5"
|
|
readme = "README.md"
|
|
keywords = ["agent", "memory", "hdf5", "vector-search", "embedding"]
|
|
categories = ["database", "science", "algorithms"]
|
|
|
|
[dependencies]
|
|
clawhdf5-format = { path = "../clawhdf5-format", version = "2.7.0", features = ["parallel", "fast-checksum"] }
|
|
clawhdf5 = { path = "../clawhdf5", version = "2.7.0" }
|
|
clawhdf5-io = { path = "../clawhdf5-io", version = "2.7.0", features = ["mmap"] }
|
|
clawhdf5-accel = { path = "../clawhdf5-accel", version = "2.7.0" }
|
|
clawhdf5-ann = { path = "../clawhdf5-ann", version = "2.7.0", optional = true }
|
|
clawhdf5-gpu = { path = "../clawhdf5-gpu", version = "2.7.0", optional = true, default-features = false }
|
|
serde = { workspace = true }
|
|
byteorder = "1"
|
|
half = { workspace = true, optional = true }
|
|
rayon = { version = "1", optional = true }
|
|
matrixmultiply = { version = "0.3", optional = true }
|
|
cblas-sys = { version = "0.1", optional = true }
|
|
tokio = { version = "1", features = ["rt", "sync", "macros", "time"], optional = true }
|
|
|
|
[target.'cfg(target_os = "macos")'.dependencies]
|
|
accelerate-src = { version = "0.3", optional = true }
|
|
|
|
[target.'cfg(not(target_os = "macos"))'.dependencies]
|
|
openblas-src = { version = "0.10", optional = true, features = ["cblas"] }
|
|
|
|
[dev-dependencies]
|
|
tempfile = { workspace = true }
|
|
criterion = { workspace = true }
|
|
rayon = "1"
|
|
tokio = { version = "1", features = ["rt-multi-thread", "sync", "macros"] }
|
|
|
|
[[bench]]
|
|
name = "bench"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "memory_bench"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "multimodal_bench"
|
|
harness = false
|
|
|
|
[features]
|
|
default = ["float16", "hnsw", "parallel"]
|
|
float16 = ["half"]
|
|
# Rayon-parallel brute-force search strategies, and a parallel bulk build of
|
|
# the HNSW index (same graph, several times faster on a multi-core machine).
|
|
parallel = ["rayon", "clawhdf5-ann?/parallel"]
|
|
# Compress embeddings with Zstd instead of deflate when
|
|
# `MemoryConfig::compression` is on. Off by default: it links libzstd (C).
|
|
zstd = ["clawhdf5/zstd"]
|
|
# HNSW approximate-nearest-neighbour acceleration for the vector stage of
|
|
# hybrid_search. On by default; the index is rebuilt from the cache on demand
|
|
# and stays self-consistent with the persisted memory store. Disable with
|
|
# `--no-default-features` (plus re-enabling other defaults) to force the exact
|
|
# linear cosine scan.
|
|
hnsw = ["clawhdf5-ann"]
|
|
agent = []
|
|
gpu = ["clawhdf5-gpu/gpu-wgpu"]
|
|
fast-math = ["matrixmultiply"]
|
|
accelerate = ["accelerate-src", "cblas-sys"]
|
|
openblas = ["openblas-src", "cblas-sys"]
|
|
async = ["tokio"]
|