Pith Number

pith:UV5ZLYXK

pith:2025:UV5ZLYXKRTCCL43BYDHMIR5PRD

not attested not anchored not stored refs pending

Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference

Chen Wang, Eun Kyung Lee, Ferran Agullo, Jordi Torres, Josep Ll. Berral, Olivier Tardieu, Pol G. Recasens, Yue Zhu

arxiv:2503.08311 v2 · 2025-03-11 · cs.DC · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UV5ZLYXKRTCCL43BYDHMIR5PRD}

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

Think Before You Grid-Search: Floor-First Triage for LLM Serving

Toward Robust and Efficient ML-Based GPU Caching for Modern Inference

Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective

Receipt and verification

First computed	2026-07-05T11:35:33.827340Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a57b95e2ea8cc425f361c0cec447af88d0533e8ac78d74112bf53981fe507ad7

Aliases

arxiv: 2503.08311 · arxiv_version: 2503.08311v2 · doi: 10.48550/arxiv.2503.08311 · pith_short_12: UV5ZLYXKRTCC · pith_short_16: UV5ZLYXKRTCCL43B · pith_short_8: UV5ZLYXK

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/UV5ZLYXKRTCCL43BYDHMIR5PRD \
  | 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: a57b95e2ea8cc425f361c0cec447af88d0533e8ac78d74112bf53981fe507ad7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "829a1182ae42f40d5963eea18d3e9d979707672237f42e8e4ccc44a1ccbb86e3",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.DC",
    "submitted_at": "2025-03-11T11:21:35Z",
    "title_canon_sha256": "584d60c9bed26f9d807aeb0e3d917ca7419fcad35d7b83d8e7cb8813f195febd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.08311",
    "kind": "arxiv",
    "version": 2
  }
}