yams/docs/benchmarks
trvon cc49704791
feat: bench harness data_dir reuse + richer telemetry, doc updates
Topology ablation bench: read YAMS_BENCH_DAEMON_DATA_DIR so multiple
daemon spawns can share a stable data_dir. Lets the topology tuner's
persisted MAB state carry over between bench reps; without this, every
fresh DaemonHarness spawn cold-starts UCB1 and picks the alphabetically-
first arm. Pairs with the TopologyTuner persistence (already on HEAD).

Bench also gains per-surface vector-leg counters (vec_unique_doc_counts,
topology_weak_routing_applied, vector_tier_skip_reason, embedding_status,
vector_db_dim/query_embedding_dim) and a modeOf reducer for categorical
metrics — Phase F1-era richer attribution carried forward.

Docs: AGENTS.md / daemon_architecture / retrieval_precision_optimization /
PROMPT-eng-codex updates from the parallel sessions.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-23 20:26:26 -04:00
..
e1_per_component_telemetry.md fix: HNSW and topology rebuilds are now batched in repair. Cleaning up from previous migration work 2026-04-21 13:58:10 -04:00
e7_adaptive_threshold.md feat: removing experiments and unifying compression in embeddings storage. 2026-04-21 18:13:37 -04:00
longmemeval_s_baseline.md feat: Improving search speed for hybrid engine. Trying best to balance speed and precision 2026-04-10 17:30:21 -04:00
multi_client_optimization_loop.md feat: optimizations for multiclient usage, updated benchmarks and ci correctness improvements to improve test runs collection 2026-04-10 13:39:59 -04:00
performance_report.md fix: small fixes for benchmarks and documentation update 2026-04-17 22:32:04 -04:00
README.md fix: updating readme and linking benchmark pages 2026-04-09 22:58:23 -04:00
retrieval_precision_optimization.md feat: bench harness data_dir reuse + richer telemetry, doc updates 2026-04-23 20:26:26 -04:00
storage_backends.md fix: fixing daemon regression for startup logic resulting in ipc eof, expanding release please to update conan file version, expanding benchmark docs 2026-03-07 21:38:35 -05:00

Benchmarks

This section is the public benchmark index for YAMS.

Each page should answer three things:

  • what workload or dataset was measured,
  • what the latest published results are,
  • how to run the benchmark locally.

Benchmark Docs

Scope

  • Public benchmark docs focus on benchmark data, workload context, and reproducible commands.
  • Internal harness plumbing and generated artifacts are intentionally omitted from public docs.
  • tested means the path is validated in this repository.
  • supported means the path exists but is not currently part of automated validation here.

When in doubt, treat tested paths as the default reference point.