Consolidate Athena test history and final MTP2 production state

2026-09-20 23:30:20 +02:00
parent fbe8c6f1e9
commit de3f8fd7aa
11 changed files with 309 additions and 11 deletions
@@ -0,0 +1,114 @@
+{
+  "args": [
+    "--model",
+    "/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf",
+    "--mmproj",
+    "/models/qwen/mmproj-BF16.gguf",
+    "--mmproj-offload",
+    "--mmproj-device",
+    "CUDA1",
+    "--alias",
+    "qwen-medium",
+    "--ctx-size",
+    "160000",
+    "--flash-attn",
+    "on",
+    "--cache-type-k",
+    "q4_0",
+    "--cache-type-v",
+    "q4_0",
+    "--cache-prompt",
+    "--cache-ram",
+    "32768",
+    "--threads",
+    "6",
+    "--threads-batch",
+    "6",
+    "--batch-size",
+    "2048",
+    "--ubatch-size",
+    "256",
+    "--parallel",
+    "2",
+    "--kv-unified",
+    "--jinja",
+    "--reasoning",
+    "auto",
+    "--reasoning-preserve",
+    "--host",
+    "0.0.0.0",
+    "--port",
+    "8080",
+    "--metrics",
+    "--fit",
+    "off",
+    "--n-gpu-layers",
+    "all",
+    "--load-mode",
+    "none",
+    "--no-ui",
+    "--temperature",
+    "1.0",
+    "--top-p",
+    "0.95",
+    "--top-k",
+    "20",
+    "--device",
+    "CUDA0,CUDA1",
+    "--main-gpu",
+    "0",
+    "--split-mode",
+    "layer",
+    "--tensor-split",
+    "85,15",
+    "--spec-type",
+    "draft-mtp",
+    "--spec-draft-n-max",
+    "2",
+    "--spec-draft-type-k",
+    "f16",
+    "--spec-draft-type-v",
+    "f16",
+    "--spec-draft-p-min",
+    "0.05"
+  ],
+  "smoke": {
+    "choices": [
+      {
+        "finish_reason": "stop",
+        "index": 0,
+        "message": {
+          "role": "assistant",
+          "content": "OK"
+        }
+      }
+    ],
+    "created": 1789939528,
+    "model": "qwen-medium",
+    "system_fingerprint": "b10964-b29c606e2",
+    "object": "chat.completion",
+    "usage": {
+      "completion_tokens": 2,
+      "prompt_tokens": 19,
+      "total_tokens": 21,
+      "prompt_tokens_details": {
+        "cached_tokens": 0
+      }
+    },
+    "id": "chatcmpl-PAF96fKOq1RJLre26QZBbmTRrk5mcFBi",
+    "timings": {
+      "cache_n": 0,
+      "prompt_n": 19,
+      "prompt_ms": 774.188,
+      "prompt_per_token_ms": 40.746736842105264,
+      "prompt_per_second": 24.54184254987161,
+      "predicted_n": 2,
+      "predicted_ms": 287.02,
+      "predicted_per_token_ms": 287.02,
+      "predicted_per_second": 3.4840777646157064,
+      "draft_n": 2,
+      "draft_n_accepted": 2
+    }
+  },
+  "time": 1789939528.283845
+}
@@ -0,0 +1,61 @@
+{
+  "checked_at": 1789937953.3488333,
+  "uptime": "22:59:13 up 3 days, 11:54,  1 user,  load average: 0.51, 0.48, 0.68",
+  "containers": {
+    "mike-ai-llama-medium": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:5e3c12c145b8045e5731b44b6b97033f24b327ae3d4a3fa85ecdd159cc844907",
+      "started": "2026-09-20T20:58:18.091639472Z"
+    },
+    "mike-ai-router": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:0448758bec6968b29263bcac0f8b4682c6d3029d626f7c12334698c11ef096bb",
+      "started": "2026-09-20T20:58:28.524893655Z"
+    },
+    "mike-ai-profile-controller": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:a5f156d94c4921e671fafa524cf9c0fe91e1cbec0113c1f19c136204d63f243f",
+      "started": "2026-09-20T20:58:28.376269054Z"
+    },
+    "mike-ai-wireguard-gateway": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:0d24e93c85a1c420b52b17666ede5fbd4672d92ab8dc28ea4ac5ba144ebc41d0",
+      "started": "2026-09-17T09:05:07.164533904Z"
+    },
+    "mike-ai-qwen3-tts": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:b363a01d08b1bbecbfc3ca6f585368fae2cfdc591f9ecca6643738369f9a9d98",
+      "started": "2026-09-20T20:16:34.144444642Z"
+    }
+  },
+  "router": {
+    "/health": {
+      "status": "ok",
+      "router": "alive"
+    },
+    "/ready": {
+      "status": "ok",
+      "router": "alive",
+      "upstream": "ready"
+    }
+  },
+  "smoke": {
+    "content": "OK",
+    "usage": {
+      "completion_tokens": 2,
+      "prompt_tokens": 19,
+      "total_tokens": 21,
+      "prompt_tokens_details": {
+        "cached_tokens": 0
+      }
+    }
+  },
+  "kernel_errors": [],
+  "gpu": "name, memory.used [MiB], memory.total [MiB], temperature.gpu\nNVIDIA GeForce RTX 3060, 10918 MiB, 12288 MiB, 43\nNVIDIA GeForce RTX 5080, 15714 MiB, 16303 MiB, 46",
+  "disk": "Filesystem      Size  Used Avail Use% Mounted on\n/dev/nvme0n1p2  868G  187G  637G  23% /\n/dev/nvme1n1p1  916G  822G   49G  95% /data"
+}