52 lines
1.6 KiB
JSON
52 lines
1.6 KiB
JSON
{
|
|
"benchmark_lanes": [
|
|
{
|
|
"concurrency_levels": [
|
|
1,
|
|
4
|
|
],
|
|
"id": "transformers-safetensors",
|
|
"recipe": "current safetensors recipe",
|
|
"runtime": "transformers"
|
|
},
|
|
{
|
|
"concurrency_levels": [
|
|
1,
|
|
4
|
|
],
|
|
"id": "llama-cpp-gguf",
|
|
"recipe": "whole-model GGUF recipe",
|
|
"runtime": "llama.cpp"
|
|
}
|
|
],
|
|
"metrics": [
|
|
"ttft_ms",
|
|
"prefill_tok_per_sec",
|
|
"decode_tok_per_sec",
|
|
"p50_latency_ms",
|
|
"p95_latency_ms",
|
|
"aggregate_throughput_tok_per_sec",
|
|
"rss_bytes",
|
|
"vram_bytes",
|
|
"artifact_bytes",
|
|
"failure_count",
|
|
"output_drift"
|
|
],
|
|
"model_target": {
|
|
"architecture": "deepseek2",
|
|
"gguf_quant": "Q2_K",
|
|
"gguf_repo": "second-state/DeepSeek-V2-Lite-Chat-GGUF",
|
|
"gguf_size_gb": 6.43,
|
|
"name": "DeepSeek-V2-Lite-Chat",
|
|
"rationale": "Smallest DeepSeek-family benchmark anchor that still points toward DeepSeek-V4-Flash; keeps the runtime on the DeepSeek2 path instead of falling back to a tiny but architecture-mismatched smoke model.",
|
|
"safetensors_repo": "deepseek-ai/DeepSeek-V2-Lite-Chat"
|
|
},
|
|
"notes": [
|
|
"Real model execution stays opt-in and must keep model artifacts on the mounted drive.",
|
|
"Use the tiny fallback only for loader plumbing smoke tests; it does not replace the architecture-aligned baseline."
|
|
],
|
|
"schema_version": 1,
|
|
"stop_condition": "Stop if GGUF does not provide a meaningful speed or fit benefit over the safetensors baseline for the chosen DeepSeek-family model target.",
|
|
"story_id": "DGR-001"
|
|
}
|