Adopt tested MTP2 for Large; retain Medium MTP3 after warmup failure

2026-09-20 22:59:50 +02:00
parent 9e836cf5fd
commit b352e29c89
29 changed files with 2340 additions and 3 deletions
@@ -0,0 +1,11 @@
+{
+  "label": "medium-mtp2",
+  "profile": "medium",
+  "ubatch": 512,
+  "split": "85,15",
+  "mtp": 2,
+  "prompts": [
+    4096
+  ],
+  "minimum_headroom_mib": 448
+}
@@ -0,0 +1,71 @@
+[
+  {
+    "time": 1789937696.1053374,
+    "gpus": [
+      {
+        "name": "NVIDIA GeForce RTX 3060",
+        "used": "6964",
+        "total": "12288",
+        "temp": "46",
+        "util": "100",
+        "pcie_gen": "3",
+        "pcie_width": "4"
+      },
+      {
+        "name": "NVIDIA GeForce RTX 5080",
+        "used": "11272",
+        "total": "16303",
+        "temp": "45",
+        "util": "0",
+        "pcie_gen": "4",
+        "pcie_width": "16"
+      }
+    ]
+  },
+  {
+    "time": 1789937698.1347463,
+    "gpus": [
+      {
+        "name": "NVIDIA GeForce RTX 3060",
+        "used": "8782",
+        "total": "12288",
+        "temp": "46",
+        "util": "0",
+        "pcie_gen": "3",
+        "pcie_width": "4"
+      },
+      {
+        "name": "NVIDIA GeForce RTX 5080",
+        "used": "15918",
+        "total": "16303",
+        "temp": "45",
+        "util": "1",
+        "pcie_gen": "4",
+        "pcie_width": "16"
+      }
+    ]
+  },
+  {
+    "time": 1789937700.1621327,
+    "gpus": [
+      {
+        "name": "NVIDIA GeForce RTX 3060",
+        "used": "4645",
+        "total": "12288",
+        "temp": "46",
+        "util": "0",
+        "pcie_gen": "3",
+        "pcie_width": "4"
+      },
+      {
+        "name": "NVIDIA GeForce RTX 5080",
+        "used": "1",
+        "total": "16303",
+        "temp": "45",
+        "util": "0",
+        "pcie_gen": "4",
+        "pcie_width": "16"
+      }
+    ]
+  }
+]
@@ -0,0 +1,15 @@
+{
+  "case": {
+    "label": "medium-mtp2",
+    "profile": "medium",
+    "ubatch": 512,
+    "split": "85,15",
+    "mtp": 2,
+    "prompts": [
+      4096
+    ],
+    "minimum_headroom_mib": 448
+  },
+  "started": 1789937694.0730917,
+  "error": "Test container exited during load"
+}
@@ -0,0 +1,75 @@
+[
+  "--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",
+  "512",
+  "--parallel",
+  "2",
+  "--kv-unified",
+  "--jinja",
+  "--reasoning",
+  "auto",
+  "--reasoning-preserve",
+  "--host",
+  "127.0.0.1",
+  "--port",
+  "5005",
+  "--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",
+  "--verbosity",
+  "3"
+]