Commit History
Yesterday
-
Card: serve with --max-model-len 32768 in Run with vLLM
Verified signatureAt the default 262,144 positions, vLLM's startup profiling pass for d3 does not fit on an 80 GB GPU, even with d3-FP8 ([discussion #2](https://huggingface.co/vllm-sr/d3/discussions/2)). The serve command now passes `--max-model-len 32768`, which covers d3's requests, and the section says why.6cce75f
6 days ago
-
Add Typed Decisions benchmark eval results (#4)
- Add Typed Decisions benchmark eval results (0cc2374f389e6536b72c10d95a6b24f5c0551794) Co-authored-by: Nathan Habib <SaylorTwift@users.noreply.huggingface.co>cf15549
8 days ago
-
Card: add Run with vLLM
Verified signature225be8b -
Card: link the free API at decision.vllm-sr.ai and the official Space
Verified signaturebb1a602
9 days ago
-
Runtime: loading checks only the files the runtime reads
Verified signature156a6d9 -
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.2fe35d1
10 days ago
-
Card: official Jev Decision Index 0.3.2 results and serving performance
Verified signaturefc2d74b
11 days ago
-
Runtime: faster System One server replies
Verified signature093cffb -
Runtime: simpler System One server
Verified signature2de0bdd -
Card: shorter vLLM Semantic Router command
Verified signatureThe "Run with vLLM Semantic Router" section now uses `vllm-sr serve -e vllm-sr/d3`: 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.5ce995d -
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 --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.7f257ad
12 days ago
-
d3 v3.1.0
Verified signaturecbff3a3 -
d3 v3.0.6
Verified signaturea443f81 -
d3 v3.0.5
Verified signature3d309f3
13 days ago
-
d3 v3.0.4
Verified signature2b02c42 -
d3 v3.0.3
Verified signaturedc6c41c -
Card: remove pending-evaluation wording
Verified signatureec58e48 -
Card: speed on AMD Instinct MI325X
Verified signature2f3af97 -
d3 v3.0.2
Verified signature216ba44 -
d3 v3.0.1
Verified signature66f305f -
d3
5d3d645