Commit History
15 days ago
-
Add Typed Decisions benchmark eval results
Verified signatureaccuracy, kl_from_gold, brier, ece on LocalLLaMA/typed-decisions test split (400 cases, 2000 decisions, one request per case). Independent run 2026-10-16; details: https://huggingface.co/buckets/SaylorTwift/typed-decisions-evalsf9cf349
16 days ago
-
Card: link the free API at decision.vllm-sr.ai and the official Space
Verified signature9c10703
17 days ago
-
Runtime: loading checks only the files the runtime reads
Verified signatured3a210a -
Card: Engine mode batches by default; engine arguments replace runtime profiles
Verified signatureNames the two measured Engine mode setups for what they were: one request per forward, the former default (exact in the chart), and batching, the default in vLLM Semantic Router from main. The engine arguments --max-num-batched-tokens, --max-num-seqs, --batch-window-ms and --dtype replace the --runtime-profile flag. README.md only; every measured number is unchanged.22ba0da
18 days ago
-
Card: official Jev Decision Index 0.3.2 results and serving performance
Verified signature99e5b1c
19 days ago
-
Runtime: faster System One server replies
Verified signature3c49f5c -
Runtime: simpler System One server
Verified signatureca41e95 -
Card: shorter vLLM Semantic Router command
Verified signatureThe "Run with vLLM Semantic Router" section now uses `vllm-sr serve -e vllm-sr/d3-lite`: the platform is detected automatically, and one line lists the `--platform` values (auto, cpu, cuda, rocm; default auto). The parity sentence keeps its measurement context (AMD Instinct MI325X). MODEL_MANIFEST.json records the new README.md (SHA-256 and size) in the same commit. Weights, runtime files and the v3.1.0 tag are unchanged.8c4ead9 -
Card: run with vLLM Semantic Router (Engine mode)
Verified signatureAdds the "Run with vLLM Semantic Router" section: install the vllm-sr CLI from the development channel, `vllm-sr serve vllm-sr/d3-lite --engine --platform rocm`, and text, image and video requests to the System One API. MODEL_MANIFEST.json records the new README.md (SHA-256 and size) in the same commit. Weights, runtime files and the v3.1.0 tag are unchanged.c91d55d
20 days ago
-
d3-lite v3.1.0
Verified signaturea8d25a9 -
d3-lite v3.0.5
Verified signature2227a85 -
d3-lite v3.0.4
Verified signature391d87f -
d3-lite v3.0.3
Verified signature0c3d3f0 -
d3-lite v3.0.2
Verified signatured82b56a
21 days ago
-
d3-lite v3.0.1
Verified signature8f29aac -
MODEL_MANIFEST.json: hash of the new banner
Verified signatureb731454 -
Update banner
Verified signature74d575a -
Model card: speed on AMD Instinct MI325X
Verified signaturef8e4725 -
d3-lite
f550a6d