docs: scrub PII/IPs from gpu-bakeoff

- Rename host alias matt-strix -> strix-halo (removes third-party name) - Move host URLs to env-var lookup (OLLAMA_*_URL), drop hardcoded IPs from harness source. Defaults: steel141 keeps localhost; pve197 and strix-halo require their env var to be set before use. - Update doc: remove the Tailscale IP and LAN-IP references, describe access paths without specific addresses. - Rename runs/matt-strix -> runs/strix-halo and patch the host field in each JSON. Harness still functional for the original author (set the env vars) and safe to share without leaking routable addresses. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 05:50:52 -04:00
parent 22af59756f
commit 91842f30cb
9 changed files with 43 additions and 21 deletions
@@ -0,0 +1,81 @@
+{
+  "host": "strix-halo",
+  "gpu": "AMD Strix Halo iGPU",
+  "vram_gb": null,
+  "model_alias": "gemma4:31b",
+  "model_tag": "gemma4:31b",
+  "prompt_key": "long",
+  "prompt_chars": 1614,
+  "num_predict": 256,
+  "num_ctx": 4096,
+  "runs": [
+    {
+      "prompt_tokens": 319,
+      "prompt_eval_ms": 97.2,
+      "prefill_tok_per_s": 3282.33,
+      "output_tokens": 256,
+      "eval_ms": 24566.1,
+      "decode_tok_per_s": 10.42,
+      "load_ms": 157.2,
+      "total_ms": 24879.5,
+      "harness_wall_s": 24.945,
+      "done_reason": "length"
+    },
+    {
+      "prompt_tokens": 319,
+      "prompt_eval_ms": 97.3,
+      "prefill_tok_per_s": 3277.8,
+      "output_tokens": 256,
+      "eval_ms": 24560.7,
+      "decode_tok_per_s": 10.42,
+      "load_ms": 162.3,
+      "total_ms": 24880.5,
+      "harness_wall_s": 24.943,
+      "done_reason": "length"
+    },
+    {
+      "prompt_tokens": 319,
+      "prompt_eval_ms": 97.4,
+      "prefill_tok_per_s": 3274.93,
+      "output_tokens": 256,
+      "eval_ms": 24559.5,
+      "decode_tok_per_s": 10.42,
+      "load_ms": 157.1,
+      "total_ms": 24876.8,
+      "harness_wall_s": 24.94,
+      "done_reason": "length"
+    }
+  ],
+  "warmup": {
+    "prompt_tokens": 319,
+    "prompt_eval_ms": 1052.0,
+    "prefill_tok_per_s": 303.23,
+    "output_tokens": 256,
+    "eval_ms": 24563.0,
+    "decode_tok_per_s": 10.42,
+    "load_ms": 167.6,
+    "total_ms": 25843.0,
+    "harness_wall_s": 25.896,
+    "done_reason": "length"
+  },
+  "summary": {
+    "prefill_tok_per_s": {
+      "min": 3274.93,
+      "median": 3277.8,
+      "max": 3282.33,
+      "n": 3
+    },
+    "decode_tok_per_s": {
+      "min": 10.42,
+      "median": 10.42,
+      "max": 10.42,
+      "n": 3
+    },
+    "total_ms": {
+      "min": 24876.8,
+      "median": 24879.5,
+      "max": 24880.5,
+      "n": 3
+    }
+  }
+}
@@ -0,0 +1,81 @@
+{
+  "host": "strix-halo",
+  "gpu": "AMD Strix Halo iGPU",
+  "vram_gb": null,
+  "model_alias": "gemma4:31b",
+  "model_tag": "gemma4:31b",
+  "prompt_key": "short",
+  "prompt_chars": 78,
+  "num_predict": 256,
+  "num_ctx": 4096,
+  "runs": [
+    {
+      "prompt_tokens": 28,
+      "prompt_eval_ms": 96.4,
+      "prefill_tok_per_s": 290.33,
+      "output_tokens": 256,
+      "eval_ms": 24049.7,
+      "decode_tok_per_s": 10.64,
+      "load_ms": 169.4,
+      "total_ms": 24372.6,
+      "harness_wall_s": 24.428,
+      "done_reason": "length"
+    },
+    {
+      "prompt_tokens": 28,
+      "prompt_eval_ms": 96.0,
+      "prefill_tok_per_s": 291.74,
+      "output_tokens": 256,
+      "eval_ms": 24046.4,
+      "decode_tok_per_s": 10.65,
+      "load_ms": 165.7,
+      "total_ms": 24365.4,
+      "harness_wall_s": 24.429,
+      "done_reason": "length"
+    },
+    {
+      "prompt_tokens": 28,
+      "prompt_eval_ms": 95.6,
+      "prefill_tok_per_s": 292.74,
+      "output_tokens": 256,
+      "eval_ms": 24065.8,
+      "decode_tok_per_s": 10.64,
+      "load_ms": 164.3,
+      "total_ms": 24385.6,
+      "harness_wall_s": 24.432,
+      "done_reason": "length"
+    }
+  ],
+  "warmup": {
+    "prompt_tokens": 28,
+    "prompt_eval_ms": 207.0,
+    "prefill_tok_per_s": 135.28,
+    "output_tokens": 256,
+    "eval_ms": 24181.8,
+    "decode_tok_per_s": 10.59,
+    "load_ms": 5509.8,
+    "total_ms": 30028.6,
+    "harness_wall_s": 30.082,
+    "done_reason": "length"
+  },
+  "summary": {
+    "prefill_tok_per_s": {
+      "min": 290.33,
+      "median": 291.74,
+      "max": 292.74,
+      "n": 3
+    },
+    "decode_tok_per_s": {
+      "min": 10.64,
+      "median": 10.64,
+      "max": 10.65,
+      "n": 3
+    },
+    "total_ms": {
+      "min": 24365.4,
+      "median": 24372.6,
+      "max": 24385.6,
+      "n": 3
+    }
+  }
+}