pith:EEWGKQH2
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
SPEED-Bench establishes a unified benchmark for speculative decoding that covers diverse semantic domains, throughput across concurrencies, and integration with production engines.
arxiv:2604.09557 v2 · 2026-02-10 · cs.DC · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{EEWGKQH2PA4OU37HDISKGOCNDL}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
SPEED-Bench establishes a unified evaluation standard for practical comparisons of SD algorithms by offering diverse semantic domains, throughput splits across concurrencies, and integration with production engines like vLLM and TensorRT-LLM.
That the qualitative data split, curated by prioritizing semantic diversity across samples, sufficiently represents real-world workloads and that integration with the named production engines accurately exposes behaviors masked by other benchmarks.
SPEED-Bench is a new standardized benchmark for speculative decoding that supplies semantically diverse qualitative data and throughput-oriented splits across concurrency levels, integrated with vLLM and TensorRT-LLM.
Cited by
Receipt and verification
| First computed | 2026-05-29T02:05:44.437764Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
212c6540fa7838ea6fe71a24a3384d1ad308f3be425f552f2322e3e1935205d2
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 212c6540fa7838ea6fe71a24a3384d1ad308f3be425f552f2322e3e1935205d2
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "219ba16ef468f7d6d98bc8dd6c07845dc2ad5977599c585d9020df519514f8ef",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.DC",
"submitted_at": "2026-02-10T16:19:56Z",
"title_canon_sha256": "b2cdf3e6cae54ea497f4b57ad966171f2db553c8a8345929034a4d94a88e77c3"
},
"schema_version": "1.0",
"source": {
"id": "2604.09557",
"kind": "arxiv",
"version": 2
}
}