Skip to content

Commit 28e1f36

Browse files
committed
Replace scenario builtins
Signed-off-by: Samuel Monson <[email protected]>
1 parent 8f1e001 commit 28e1f36

File tree

6 files changed

+50
-12
lines changed

6 files changed

+50
-12
lines changed

src/guidellm/benchmark/scenarios/chat.json

Lines changed: 0 additions & 6 deletions
This file was deleted.
Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
{
2+
"description": "Prefill/Decode balanced scenario. Note: This scenario is optimized for NVIDIA H200s and may need to be adjusted for other hardware.",
3+
"profile": "concurrent",
4+
"request-type": "text_completions",
5+
"data": {
6+
"prompt_tokens": 1000,
7+
"output_tokens": 1000
8+
},
9+
"rate": [1, 50, 100, 200, 300, 500, 650],
10+
"max-seconds": "600"
11+
}
Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
{
2+
"description": "Prefill heavy scenario. Note: This scenario is optimized for NVIDIA H200s and may need to be adjusted for other hardware.",
3+
"profile": "concurrent",
4+
"request-type": "text_completions",
5+
"data": {
6+
"prompt_tokens": 2048,
7+
"output_tokens": 128
8+
},
9+
"rate": [1, 50, 100, 200, 300, 500, 650],
10+
"max-seconds": "600"
11+
}
Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,17 @@
1+
{
2+
"description": "Generation heavy scenario with sequence length variance. Note: This scenario is optimized for NVIDIA H200s and may need to be adjusted for other hardware.",
3+
"profile": "concurrent",
4+
"request-type": "text_completions",
5+
"data": {
6+
"prompt_tokens": 512,
7+
"prompt_tokens_stdev": 128,
8+
"prompt_tokens_min": 1,
9+
"prompt_tokens_max": 1024,
10+
"output_tokens": 2048,
11+
"output_tokens_stdev": 512,
12+
"output_tokens_min": 1,
13+
"output_tokens_max": 4096
14+
},
15+
"rate": [1, 5, 25, 50, 100, 150, 200, 250, 300, 400, 500, 650],
16+
"max-seconds": "600"
17+
}
Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
{
2+
"description": "Large context scenario. Note: This scenario is optimized for NVIDIA H200s and may need to be adjusted for other hardware.",
3+
"profile": "concurrent",
4+
"request-type": "text_completions",
5+
"data": {
6+
"prompt_tokens": 8000,
7+
"output_tokens": 1000
8+
},
9+
"rate": [1, 50, 100, 200, 300, 500, 650],
10+
"max-seconds": "600"
11+
}

src/guidellm/benchmark/scenarios/rag.json

Lines changed: 0 additions & 6 deletions
This file was deleted.

0 commit comments

Comments
 (0)