Skip to content

[Docs] File the performance inventory and close the PLE read-path knobs #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rwkeyes merged 1 commit into from
Nov 14, 2026
Merged

[Docs] File the performance inventory and close the PLE read-path knobs #14

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
263 changes: 263 additions & 0 deletions dirigo-results/0.2.13-port/ple-sweep/bench-ple-b.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,263 @@
[
{
"label": "ple-b",
"kind": "warmup",
"trial": 0,
"wall_s": 0.3168691350147128,
"metrics": {
"prompt_tokens": 15.0,
"reused": 0.0,
"fresh": 15.0,
"prefill_ms": 209.0,
"prefill_tps": 71.7,
"generated": 2.0,
"decode_ms": 82.0,
"decode_tps": 24.4
},
"usage": {
"prompt_tokens": 15,
"completion_tokens": 2,
"total_tokens": 17,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "READY"
}
},
{
"label": "ple-b",
"kind": "fresh",
"trial": 1,
"wall_s": 4.852005727007054,
"metrics": {
"prompt_tokens": 4210.0,
"reused": 0.0,
"fresh": 4210.0,
"prefill_ms": 3214.0,
"prefill_tps": 1310.1,
"generated": 128.0,
"decode_ms": 1633.0,
"decode_tps": 78.4
},
"usage": {
"prompt_tokens": 4210,
"completion_tokens": 128,
"total_tokens": 4338,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The source code defines a series of 140 exported functions, named `rule0` through `rule139`, each accepting a single numeric argument `x`. Every function follows an identical logical pattern: it checks if the input `x` is strictly equal to the integer value embedded in its name (denoted as $n$); if this condition is true, the function returns $x + n + 1$, and if false, it returns $x - n$. Consequently, each specific rule acts as a conditional modifier that either increments the input by one more than its index or decrements it by its index, depending"
}
},
{
"label": "ple-b",
"kind": "followup",
"trial": 1,
"wall_s": 2.1206404130207375,
"metrics": {
"prompt_tokens": 4451.0,
"reused": 4337.0,
"fresh": 114.0,
"prefill_ms": 429.0,
"prefill_tps": 265.7,
"generated": 128.0,
"decode_ms": 1687.0,
"decode_tps": 75.9
},
"usage": {
"prompt_tokens": 4451,
"completion_tokens": 128,
"total_tokens": 4579,
"prompt_tokens_details": {
"cached_tokens": 4337
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The most relevant boundary case is the **exact integer equality check** (`x === n`), which acts as a strict gatekeeper for the \"increment\" branch. For any function `ruleN`, if the input `x` is exactly equal to `N`, the function returns `N + 1` (a positive offset); otherwise, it returns `x - N`. This creates a discontinuity in behavior: inputs just below or above `N` result in subtraction, while `N` itself results in addition.\n\nThe **smallest useful regression test** targets this specific equality condition because it is the only case where the output"
}
},
{
"label": "ple-b",
"kind": "fresh",
"trial": 2,
"wall_s": 8.365401799965184,
"metrics": {
"prompt_tokens": 8830.0,
"reused": 0.0,
"fresh": 8830.0,
"prefill_ms": 6873.0,
"prefill_tps": 1284.8,
"generated": 128.0,
"decode_ms": 1486.0,
"decode_tps": 86.1
},
"usage": {
"prompt_tokens": 8830,
"completion_tokens": 128,
"total_tokens": 8958,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The source code defines a series of exported functions named `rule0` through `rule279`, each accepting a single numeric argument `x`. Every function follows an identical logical structure: it checks if the input `x` is strictly equal to the integer value embedded in its name (e.g., `rule5` checks for `5`). If this condition is true, the function returns `x + 1`; otherwise, it returns `x - 1`. Consequently, each specific rule acts as a conditional modifier that increments the input by one only when the input matches the rule's index, and decrements the input by one"
}
},
{
"label": "ple-b",
"kind": "followup",
"trial": 2,
"wall_s": 1.9242842710227706,
"metrics": {
"prompt_tokens": 9071.0,
"reused": 8958.0,
"fresh": 113.0,
"prefill_ms": 418.0,
"prefill_tps": 270.6,
"generated": 128.0,
"decode_ms": 1503.0,
"decode_tps": 85.2
},
"usage": {
"prompt_tokens": 9071,
"completion_tokens": 128,
"total_tokens": 9199,
"prompt_tokens_details": {
"cached_tokens": 8958
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The most relevant boundary case is the **exact match condition** where `x` equals the rule's index (e.g., calling `rule5(5)`), which triggers the increment branch (`x + 1`) rather than the decrement branch (`x - 1`). This distinguishes the function from a simple arithmetic operation and validates the core logic.\n\nThe **smallest useful regression test** is:\n```javascript\nassert(rule0(0) === 1); // Boundary: x=0 matches rule index, returns 0+1=1\nassert(rule0(-1) === -2); // Negative input:"
}
},
{
"label": "ple-b",
"kind": "fresh",
"trial": 3,
"wall_s": 4.735613274038769,
"metrics": {
"prompt_tokens": 4210.0,
"reused": 0.0,
"fresh": 4210.0,
"prefill_ms": 3212.0,
"prefill_tps": 1310.8,
"generated": 128.0,
"decode_ms": 1520.0,
"decode_tps": 84.2
},
"usage": {
"prompt_tokens": 4210,
"completion_tokens": 128,
"total_tokens": 4338,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The source code defines a series of 140 exported functions, named `rule0` through `rule139`, each accepting a single numeric argument `x`. Every function follows an identical logical structure: it checks if the input `x` is strictly equal to the integer value embedded in its name (denoted as $n$). If this condition is true, the function returns $x + n + 1$; otherwise, it returns $x - n$. Consequently, for any given function `ruleN`, the output is $2N + 1$ when the input matches $N$, and $x -"
}
},
{
"label": "ple-b",
"kind": "followup",
"trial": 3,
"wall_s": 2.334400308027398,
"metrics": {
"prompt_tokens": 4451.0,
"reused": 4203.0,
"fresh": 248.0,
"prefill_ms": 646.0,
"prefill_tps": 383.8,
"generated": 128.0,
"decode_ms": 1685.0,
"decode_tps": 76.0
},
"usage": {
"prompt_tokens": 4451,
"completion_tokens": 128,
"total_tokens": 4579,
"prompt_tokens_details": {
"cached_tokens": 4203
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The most relevant boundary case is the **exact match condition** where `x === n` (the function's index), because this triggers the unique \"addition\" branch (`x + n + 1`) rather than the default \"subtraction\" branch (`x - n`). This is critical because it represents the only point where the function's behavior deviates from a simple linear transformation, and it is the only case where the output is positive and larger than the input.\n\nThe **smallest useful regression test** should verify this boundary condition for at least one representative function (e.g., `rule0` or `rule13"
}
},
{
"label": "ple-b",
"kind": "fresh",
"trial": 4,
"wall_s": 7.797196410014294,
"metrics": {
"prompt_tokens": 8830.0,
"reused": 0.0,
"fresh": 8830.0,
"prefill_ms": 6292.0,
"prefill_tps": 1403.4,
"generated": 128.0,
"decode_ms": 1500.0,
"decode_tps": 85.4
},
"usage": {
"prompt_tokens": 8830,
"completion_tokens": 128,
"total_tokens": 8958,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The source code defines a series of exported functions named `rule0` through `rule279`, each accepting a single numeric argument `x`. Every function follows an identical logical pattern: it checks if the input `x` is strictly equal to the integer value embedded in its name (e.g., `rule5` checks for `5`). If this condition is true, the function returns `x + 1`; otherwise, it returns `x - 1`. Consequently, each specific rule acts as a conditional modifier that increments the input by one only when the input matches the rule's index, and decrements the input by one"
}
},
{
"label": "ple-b",
"kind": "followup",
"trial": 4,
"wall_s": 1.8936358939972706,
"metrics": {
"prompt_tokens": 9071.0,
"reused": 8958.0,
"fresh": 113.0,
"prefill_ms": 417.0,
"prefill_tps": 271.0,
"generated": 128.0,
"decode_ms": 1473.0,
"decode_tps": 86.9
},
"usage": {
"prompt_tokens": 9071,
"completion_tokens": 128,
"total_tokens": 9199,
"prompt_tokens_details": {
"cached_tokens": 8958
}
},
"finish_reason": "length",
"message": {
"role": "assistant",
"content": "The most relevant boundary case is the **exact match condition** where `x` equals the rule's index (e.g., `rule5(5)`), which triggers the increment branch (`x + 1`) rather than the decrement branch (`x - 1`). This distinguishes the function from a simple arithmetic operation and validates the core logic.\n\nThe **smallest useful regression test** is:\n```javascript\nassert(rule0(0) === 1); // Boundary: x=0 matches rule index, returns 0+1=1\nassert(rule0(-1) === -2); // Negative input: does"
}
}
]
Loading
Loading