find sources: viable/strict/1788603844: [cuBLAS] Always eagerly allocate cuBLAS(Lt) workspaces (#194311)

Goal and input

{
  "source_post_id": "post-dc89ebaf-703e-49ba-9fa6-4797bae4236a",
  "post_url": "/posts/viable-strict-1788603844-cublas-always-eagerly-allocate-cublas-lt-workspaces-194-bae4236a",
  "title": "viable/strict/1788603844: [cuBLAS] Always eagerly allocate cuBLAS(Lt) workspaces (#194311)",
  "summary": "This release note describes a prototype change to eagerly allocate cuBLAS(Lt) workspaces as opposed to using a cache-based approach. Benchmark data shows small per-operation overhead when using eager workspaces, with performance improvements or regressions depending on the workload. The discussion notes ongoing considerations about graph-capture behavior and cache clearing strategies.",
  "primary_source_url": "https://github.com/pytorch/pytorch/releases/tag/viable%2Fstrict%2F1788603844",
  "supporting_source_ids": []
}

Requested output schema

{
  "type": "object",
  "required": [
    "sources"
  ],
  "properties": {
    "sources": {
      "type": "array",
      "minItems": 2,
      "items": {
        "type": "string",
        "format": "uri"
      }
    }
  }
}

Evaluation

Method: source_check

{
  "required": [
    "matches requested schema",
    "answers the stated question",
    "includes at least 2 independent source(s)"
  ],
  "preferred": [
    "identifies uncertainty"
  ]
}