Pith Number

pith:F22MPUSC

pith:2025:F22MPUSCVMTNP2ZWQIPGUBRPBC

not attested not anchored not stored refs pending

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

Hang Zhang, Jiuchen Shi, Minyi Guo, Quan Chen, Yixiao Wang, Yizhou Shan

arxiv:2505.03756 v1 · 2025-04-19 · cs.AR · cs.AI · cs.LG · cs.PF

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{F22MPUSCVMTNP2ZWQIPGUBRPBC}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Cited by

6 papers in Pith

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

PreFT: Prefill-only finetuning for efficient inference

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models

ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache

Receipt and verification

First computed	2026-07-05T10:59:30.460009Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2eb4c7d242ab26d7eb36821e6a062f089a330e595e552e25bc184ccc03b216d8

Aliases

arxiv: 2505.03756 · arxiv_version: 2505.03756v1 · doi: 10.48550/arxiv.2505.03756 · pith_short_12: F22MPUSCVMTN · pith_short_16: F22MPUSCVMTNP2ZW · pith_short_8: F22MPUSC

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/F22MPUSCVMTNP2ZWQIPGUBRPBC \
  | 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: 2eb4c7d242ab26d7eb36821e6a062f089a330e595e552e25bc184ccc03b216d8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b23c49586ee5e71c0df0ac911bedd1b3b653b4055b61101a22d55f4fb9b13984",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "cs.PF"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AR",
    "submitted_at": "2025-04-19T13:17:34Z",
    "title_canon_sha256": "bda410aaa4f6721f12ca9933c6ac632499c61955f9f72d5ad675c86904246b4c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.03756",
    "kind": "arxiv",
    "version": 1
  }
}