60 lines
1.8 KiB
JSON
60 lines
1.8 KiB
JSON
{
|
|
"context_limit": 131072,
|
|
"batch_token_limit": 2048,
|
|
"observed_attention_block_size": 1600,
|
|
"graph_capture_sizes": [
|
|
1,
|
|
2,
|
|
4,
|
|
8,
|
|
12
|
|
],
|
|
"nsys_version": "NVIDIA Nsight Systems version 2025.3.2.474-253236389321v0",
|
|
"trace_cases": {
|
|
"1": "short",
|
|
"2": "fresh-32768",
|
|
"3": "reused-32768"
|
|
},
|
|
"files": {
|
|
"graph/trace.2.nsys-rep": {
|
|
"bytes": 7688024,
|
|
"sha256": "443a6e052586d3f4bfe7c6f1492500e495374e8e52e6de5766a437e53d73d146"
|
|
},
|
|
"graph/trace.3.nsys-rep": {
|
|
"bytes": 4115977,
|
|
"sha256": "15e7602b8dd8d92e9f295fcc1a24df4a6245a36339555c83f04dda32c7d5dc86"
|
|
},
|
|
"graph/trace.1.nsys-rep": {
|
|
"bytes": 9244219,
|
|
"sha256": "4eceb2f5241678ac387064369ccfb485d741dec140d0a1ace46866da0d70e687"
|
|
},
|
|
"eager/trace.2.nsys-rep": {
|
|
"bytes": 8540396,
|
|
"sha256": "543a9c1a5698de7e2ce7fe9e25dab546d64236e0f6f2014648223f664ff967a1"
|
|
},
|
|
"eager/trace.3.nsys-rep": {
|
|
"bytes": 4635497,
|
|
"sha256": "af251e99de398302611f691f39073e1a48ae766bd9473931b2437c46e2e42227"
|
|
},
|
|
"eager/trace.1.nsys-rep": {
|
|
"bytes": 15842503,
|
|
"sha256": "0390fdffffaeee0b78809d64cbf8696e8301d5730de36c2d67da4e1aa18bc5d0"
|
|
},
|
|
"vllm_ple_mmap.original.py": {
|
|
"bytes": 40227,
|
|
"sha256": "02adb76b789f9fccf472e922e3be7b4b2a95962ae7d7c3eb99bfeac6052dccad"
|
|
},
|
|
"cudagraph_utils.original.py": {
|
|
"bytes": 46652,
|
|
"sha256": "e123e808a8b6a616f69cc97f8b0d25d77f0eb35d8ebc91c4cdbc505f649927c0"
|
|
},
|
|
"vllm_ple_mmap.profile.py": {
|
|
"bytes": 40773,
|
|
"sha256": "2dff4fe71a5f2f5a8579af09eebf798d49da0d1554a56819ab475b86aebe17e4"
|
|
},
|
|
"cudagraph_utils.profile.py": {
|
|
"bytes": 47119,
|
|
"sha256": "ef6dccbd27c6b109691a2ab2b9a74cc08c1d3055498ff91638f78af1fe5faf66"
|
|
}
|
|
}
|
|
} |