Validate Medium microbatch 256 with authorized lower reserve

2026-09-20 21:31:01 +02:00
1 parent ba808e105b
commit c78a083d4c
@@ -33,3 +33,11 @@ Judge walltime, prompt/decode rates, VRAM and the three-needle recall together.
 only461MiB free on5080, below the512MiB guard. No256 inference was executed.
 Args differ only in --ubatch-size. Production512 restored and checked. See
 ../../docs/MEDIUM_MICROBATCH_20260920.md. Do not claim a256 speedup or quality result.
+
+## Explicitly authorized lower-reserve follow-up
+
+reserve448.json lowers only this256 case to448MiB loaded free-memory minimum.
+It passed all three short probes: +7.1% prefill, short decodes essentially tied.
+Recorded peak free memory443MiB; the guard is a startup threshold, not a reserved
+allocation or runtime minimum. No full160K/vision/concurrency qualification.
+Production512 restored. See reserve448-comparison.json and reserve448-restore.json.
@@ -0,0 +1,30 @@
+[
+  {
+    "metric": "Deutsch",
+    "ub512": 57.15738655264799,
+    "ub256": 57.501411483474186,
+    "percent_change": 0.6018905894329407,
+    "identical_output_text": true
+  },
+  {
+    "metric": "Code",
+    "ub512": 74.94202496673532,
+    "ub256": 75.46417601433642,
+    "percent_change": 0.6967399771127925,
+    "identical_output_text": true
+  },
+  {
+    "metric": "Prefill24674",
+    "ub512": 1782.0307827509184,
+    "ub256": 1909.171738718156,
+    "percent_change": 7.134610535232744,
+    "identical_output_text": false
+  },
+  {
+    "metric": "DecodeAfter24674",
+    "ub512": 54.7725897809568,
+    "ub256": 60.0406255316709,
+    "percent_change": 9.61801472558026,
+    "identical_output_text": false
+  }
+]
@@ -0,0 +1,61 @@
+{
+  "checked_at": 1789932566.9422781,
+  "uptime": "21:29:26 up 3 days, 10:24,  1 user,  load average: 0.70, 0.42, 0.44",
+  "containers": {
+    "mike-ai-llama-medium": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:5e3c12c145b8045e5731b44b6b97033f24b327ae3d4a3fa85ecdd159cc844907",
+      "started": "2026-09-20T19:28:57.246456642Z"
+    },
+    "mike-ai-router": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:0448758bec6968b29263bcac0f8b4682c6d3029d626f7c12334698c11ef096bb",
+      "started": "2026-09-20T19:29:07.653040573Z"
+    },
+    "mike-ai-profile-controller": {
+      "running": true,
+      "health": "healthy",
+      "image": "sha256:a5f156d94c4921e671fafa524cf9c0fe91e1cbec0113c1f19c136204d63f243f",
+      "started": "2026-09-20T19:29:07.536349965Z"
+    },
+    "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": "2026-09-19T13:47:00.227813668Z"
+    }
+  },
+  "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, 10920 MiB, 12288 MiB, 45\nNVIDIA GeForce RTX 5080, 15714 MiB, 16303 MiB, 49",
+  "disk": "Filesystem      Size  Used Avail Use% Mounted on\n/dev/nvme0n1p2  868G  187G  637G  23% /\n/dev/nvme1n1p1  916G  821G   49G  95% /data"
+}
@@ -0,0 +1,17 @@
+[
+  {
+    "label": "medium-ub256-reserve448",
+    "model": "pure",
+    "ctx": 160000,
+    "parallel": 2,
+    "single": false,
+    "split": "85,15",
+    "ubatch": 256,
+    "mtp": 3,
+    "vision": true,
+    "prompts": [
+      24576
+    ],
+    "minimum_headroom_mib": 448
+  }
+]