01d4ad9c7b
openpay/ (+3 crates, ~8400 LOC, 162 tests)
op-iso8583/ ISO 8583 messages for direct acquirer / card-network
connectivity. MTIs, primary+secondary bitmaps, full
DE catalogue, BCD/ASCII/EBCDIC/LLVAR/LLLVAR codecs,
five dialects (Visa Base I, Mastercard MDS, Amex GNS,
Discover, JCB), network-management messages
(sign-on/echo/cutover), DE 55 EMV TLV.
op-mobile-wallets/ Apple Pay (ECDH-P256 + AES-256-GCM), Google Pay ECv2
(ECDH + HKDF + AES-256-CTR + HMAC), Samsung Pay. PAN
never leaves the decryption boundary as a String;
lands in VaultRef. No-PAN-leakage assertions per
wallet.
op-routing/ Least-cost routing + MCC-aware routing + intelligent
retry / soft-decline recovery. 231-MCC catalogue.
Real ISO 8583 DE-39 soft/hard decline taxonomies.
smart-byte/smart-byte-rs/ (+3 crates, ~7100 LOC, 96 tests)
smart-byte-vc/ W3C Verifiable Credentials 2.0: VCDM, presentations,
Data Integrity proofs (eddsa-jcs-2022), VC-JWT,
SD-JWT (selective disclosure), Bitstring Status
List 2021. Cargo-bridge maps VCs to Smart Byte
envelopes with SAID stability.
smart-byte-did/ W3C DID resolution: did:key (Ed25519/P-256/secp256k1),
did:web (HTTPS), did:peer (numalgo 2+4), did:jwk,
did:ion (feature-gated stub). DID URL dereferencer.
smart-byte-pq/ Post-quantum signatures: ML-DSA-44/65/87 (FIPS 204),
SLH-DSA across 12 parameter sets (FIPS 205), FN-DSA
(draft FIPS 206, feature-gated). Hybrid Ed25519 +
ML-DSA pattern for the transition. Secret-key
zeroize-on-drop.
eoc/eoc-rs/ (+3 crates, ~6450 LOC, 76 tests)
eoc-vendor-api/ NeuralBackend implementations: Anthropic, OpenAI,
Google, Mistral, Cohere, Groq, Together, Fireworks.
SSE streaming. Prompt-caching where supported.
Joule estimates per published energy coefficient
(12-model curated table).
eoc-embeddings/ 21 embedding models behind one Embedder trait:
OpenAI v3 (3), Cohere v3 (3), Voyage (5), Mistral,
Jina, plus local ONNX (BGE x3, nomic, mxbai, GTE,
E5) behind 'local' feature. Matryoshka-style
dimension projection. Per-content-hash cache.
eoc-route-learned/ RouteLLM-style matrix-factorisation router +
multinomial-logreg classifier + LinUCB / Thompson
bandits for online learning. LearnedCascade wraps
the rule-based cascade with a confidence-threshold
skip policy. Synthetic-eval accuracy: MF 0.935,
LogReg 0.980.
Quality:
- cargo check across all three workspaces: clean
- cargo clippy --all-targets -- -D warnings on every new crate: clean
- 334 new tests total; all passing
- #![forbid(unsafe_code)] across every new crate
- No unwrap/expect outside #[cfg(test)]
Rust 1.95.0 edition 2024 (inherited via root rust-toolchain.toml).
66 lines
2.7 KiB
JSON
66 lines
2.7 KiB
JSON
{
|
|
"_schema_version": 1,
|
|
"_note": "Per-token energy coefficients (joules). Sourced where possible from the HuggingFace AI Energy Score corpus and published vendor reports. Where no public number exists the coefficient is documented as 'vendor-undisclosed' and derived from order-of-magnitude analysis (model parameter count * dense-FLOPs-per-token * datacenter PUE / per-token throughput). All numbers are ESTIMATES; the JouleCost is always tagged JouleSource::Estimated.",
|
|
"profiles": {
|
|
"claude-3-5-sonnet": {
|
|
"joules_per_input_token": 0.10,
|
|
"joules_per_output_token": 0.50,
|
|
"source": "HuggingFace AI Energy Score + Anthropic published reports (claude-3.5-sonnet, 2024)"
|
|
},
|
|
"claude-3-opus": {
|
|
"joules_per_input_token": 0.30,
|
|
"joules_per_output_token": 1.20,
|
|
"source": "vendor-undisclosed; estimator derived from parameter-count ratio vs claude-3.5-sonnet"
|
|
},
|
|
"claude-3-haiku": {
|
|
"joules_per_input_token": 0.03,
|
|
"joules_per_output_token": 0.15,
|
|
"source": "vendor-undisclosed; estimator derived from claude-3-haiku FLOPs/token reports"
|
|
},
|
|
"gpt-4o": {
|
|
"joules_per_input_token": 0.10,
|
|
"joules_per_output_token": 0.40,
|
|
"source": "HuggingFace AI Energy Score (gpt-4o, 2024)"
|
|
},
|
|
"gpt-4o-mini": {
|
|
"joules_per_input_token": 0.02,
|
|
"joules_per_output_token": 0.08,
|
|
"source": "HuggingFace AI Energy Score (gpt-4o-mini, 2024)"
|
|
},
|
|
"gpt-4.1": {
|
|
"joules_per_input_token": 0.12,
|
|
"joules_per_output_token": 0.48,
|
|
"source": "vendor-undisclosed; estimator derived from gpt-4o coefficient + OpenAI capacity disclosures"
|
|
},
|
|
"o3": {
|
|
"joules_per_input_token": 0.50,
|
|
"joules_per_output_token": 4.00,
|
|
"source": "vendor-undisclosed; estimator inflated for hidden reasoning-token expansion (4-8x output token amplification)"
|
|
},
|
|
"gemini-1.5-pro": {
|
|
"joules_per_input_token": 0.08,
|
|
"joules_per_output_token": 0.40,
|
|
"source": "Google Sustainability Report 2024 + HuggingFace AI Energy Score (gemini-1.5)"
|
|
},
|
|
"gemini-1.5-flash": {
|
|
"joules_per_input_token": 0.02,
|
|
"joules_per_output_token": 0.10,
|
|
"source": "Google Sustainability Report 2024"
|
|
},
|
|
"llama-3.1-70b": {
|
|
"joules_per_input_token": 0.07,
|
|
"joules_per_output_token": 0.35,
|
|
"source": "HuggingFace AI Energy Score (llama-3.1-70b)"
|
|
},
|
|
"llama-3.1-8b": {
|
|
"joules_per_input_token": 0.01,
|
|
"joules_per_output_token": 0.05,
|
|
"source": "HuggingFace AI Energy Score (llama-3.1-8b)"
|
|
},
|
|
"mixtral-8x7b": {
|
|
"joules_per_input_token": 0.04,
|
|
"joules_per_output_token": 0.20,
|
|
"source": "HuggingFace AI Energy Score (mixtral-8x7b) + Mistral published efficiency reports"
|
|
}
|
|
}
|
|
}
|