feat(model-ports): add phi3_mini, minicpm3_4b, bitnet_2b

.github/ci/benchmark_config.json

@@ -107,12 +107,16 @@
         },
         {
           "address": "0x02000000",
-          "paths": ["yolo/weights_region.bin"],
+          "paths": [
+            "yolo/weights_region.bin"
+          ],
           "required": true
         },
         {
           "address": "0x04A00000",
-          "paths": ["yolo/coco_room_000139_raw_480x640x3_uint8_rgb.bin"],
+          "paths": [
+            "yolo/coco_room_000139_raw_480x640x3_uint8_rgb.bin"
+          ],
           "required": true
         }
       ],
@@ -122,15 +126,21 @@
         "image_count": 5,
         "min_image_count": 5,
         "reference_contract": ".github/ci/reference/yolo.json",
-        "source_shape": [480, 640, 3]
+        "source_shape": [
+          480,
+          640,
+          3
+        ]
       },
       "benchmark_cases": [
         {
           "name": "coco_room_000139",
           "file_loads": [
             {
               "address": "0x04A00000",
-              "paths": ["yolo/coco_room_000139_raw_480x640x3_uint8_rgb.bin"],
+              "paths": [
+                "yolo/coco_room_000139_raw_480x640x3_uint8_rgb.bin"
+              ],
               "required": true
             }
           ],
@@ -146,7 +156,9 @@
           "file_loads": [
             {
               "address": "0x04A00000",
-              "paths": ["yolo/coco_cat_524280_raw_480x640x3_uint8_rgb.bin"],
+              "paths": [
+                "yolo/coco_cat_524280_raw_480x640x3_uint8_rgb.bin"
+              ],
               "required": true
             }
           ],
@@ -162,7 +174,9 @@
           "file_loads": [
             {
               "address": "0x04A00000",
-              "paths": ["yolo/coco_giraffes_296969_raw_480x640x3_uint8_rgb.bin"],
+              "paths": [
+                "yolo/coco_giraffes_296969_raw_480x640x3_uint8_rgb.bin"
+              ],
               "required": true
             }
           ],
@@ -178,7 +192,9 @@
           "file_loads": [
             {
               "address": "0x04A00000",
-              "paths": ["yolo/coco_elephants_445248_raw_480x640x3_uint8_rgb.bin"],
+              "paths": [
+                "yolo/coco_elephants_445248_raw_480x640x3_uint8_rgb.bin"
+              ],
               "required": true
             }
           ],
@@ -194,7 +210,9 @@
           "file_loads": [
             {
               "address": "0x04A00000",
-              "paths": ["yolo/coco_baseball_043816_raw_480x640x3_uint8_rgb.bin"],
+              "paths": [
+                "yolo/coco_baseball_043816_raw_480x640x3_uint8_rgb.bin"
+              ],
               "required": true
             }
           ],
@@ -234,17 +252,24 @@
       "file_loads": [
         {
           "address": "0x0",
-          "paths": ["zero2m.bin", "common/zero2m.bin"],
+          "paths": [
+            "zero2m.bin",
+            "common/zero2m.bin"
+          ],
           "required": true
         },
         {
           "address": "0x2000",
-          "paths": ["dncnn/dncnn20l64_input.bin"],
+          "paths": [
+            "dncnn/dncnn20l64_input.bin"
+          ],
           "required": true
         },
         {
           "address": "0x14000",
-          "paths": ["dncnn/dncnn20l64_weights.bin"],
+          "paths": [
+            "dncnn/dncnn20l64_weights.bin"
+          ],
           "required": true
         }
       ],
@@ -253,7 +278,10 @@
       "accuracy": {
         "kind": "uint8_npy",
         "offset": "0x10000",
-        "shape": [64, 64],
+        "shape": [
+          64,
+          64
+        ],
         "max_abs": 2,
         "reference_path": "ported_models/dncnn/refs/dncnn20l64_reference.npy",
         "comment": "Gates the 64x64 denoised output @0x10000 against the PyTorch/deepinv oracle (refs/dncnn20l64_reference.npy, produced by scripts/gen_dncnn_oracle.py running deepinv.models.DnCNN on the pinned weights). Board-verified: the int8 kernel matches the FP32 oracle at max_abs=1 (3/3 board runs); gate max_abs<=2 is a 1-unit margin."
@@ -315,6 +343,12 @@
     },
     "smolvlm_500m": {
       "config": "ported_models/llama_cpp_et/benchmarks/smolvlm_500m.json"
+    },
+    "phi3_mini": {
+      "config": "ported_models/llama_cpp_et/benchmarks/phi3_mini.json"
+    },
+    "minicpm3_4b": {
+      "config": "ported_models/llama_cpp_et/benchmarks/minicpm3_4b.json"
     }
   }
 }

ported_models/bitnet_2b/docs/RECIPE.md

@@ -0,0 +1,66 @@
+# BitNet-b1.58-2B-4T -- Negative Result
+
+## Summary
+
+Attempted to add `microsoft/bitnet-b1.58-2B-4T` (2B-parameter, native
+1.58-bit ternary weight causal LM) to the `llama.cpp-et` framework. **Does
+not load with this repo's vendored `llama.cpp-et` submodule.** No
+model-ports claim is filed for this model; this recipe documents the
+failure rather than a working port.
+
+## Model Reference
+
+- **Source**: `microsoft/bitnet-b1.58-2B-4T` (Hugging Face), revision
+  `04c3b9ad9361b824064a1f25ea60a8be9599b127`
+- **License**: MIT
+- **GGUF source**: `microsoft/bitnet-b1.58-2B-4T-gguf` (official), file
+  `ggml-model-i2_s.gguf`,
+  `sha256=4221b252fdd5fd25e15847adfeb5ee88886506ba50b8a34548374492884c2162`
+  (verified locally against the downloaded file)
+- GGUF metadata (read via a minimal custom KV-only parser, since the
+  installed `gguf` PyPI package's tensor-dtype enum doesn't recognize this
+  file's dtype either): `general.architecture = bitnet-b1.58`, 332 tensors.
+
+## Root cause: confirmed, not speculative
+
+Built a plain CPU-only (`GGML_ET=OFF`) configuration of the exact vendored
+`llama.cpp-et` source in this repo and tried to load the file with
+`llama-perplexity`. It fails at model load, before any ET-specific code
+runs at all:
+
+```
+gguf_init_from_file_impl: tensor 'blk.0.ffn_down.weight' of type 36
+(TYPE_IQ4_NL_4_4 REMOVED, use IQ4_NL with runtime repacking) has 6912
+elements per row, not a multiple of block size (0)
+gguf_init_from_file_impl: failed to read tensor info
+llama_model_load: error loading model: llama_model_loader: failed to load
+model from ggml-model-i2_s.gguf
+```
+
+This repo's vendored `llama.cpp-et` fork is from a point in llama.cpp's
+history where GGML tensor-type id 36 was `TYPE_IQ4_NL_4_4`, since removed
+upstream. BitNet's official GGUF export uses type id 36 for its native
+`i2_s` ternary format. The two collide: this fork's tensor-type enum
+interprets BitNet's ternary tensors as a stale, incompatible legacy type,
+and rejects the file outright at the format-parsing stage -- before
+reaching any question of whether the ET backend's `MUL_MAT` could handle
+ternary matmul.
+
+## Why no claim is filed
+
+The port genuinely does not run, on CPU or otherwise, with this repo's
+current vendored source. Filing a model-ports claim for something that
+doesn't load would be exactly the kind of unsubstantiated submission this
+process is meant to prevent. This is the same category as this campaign's
+other documented negative results (RWKV-6, PLaMo-2 -- both blocked on
+missing `GGML_OP_CPY` support) -- a real, reproducible incompatibility,
+not a hedge or a "maybe."
+
+## What would need to change
+
+Either this repo's vendored `llama.cpp-et` needs to be updated past the
+point where type id 36 was reused for ternary support (a submodule bump,
+out of scope for a model-port PR), or BitNet's GGUF would need
+re-exporting against an older, non-conflicting tensor-type scheme (not
+attempted -- would change the model's actual on-disk representation, not
+just add board wiring).

ported_models/llama_cpp_et/artifacts.json

@@ -485,6 +485,42 @@
       "sha256": "d1eb8b6b23979205fdf63703ed10f788131a3f812c7b1f72e0119d5d81295150",
       "size_bytes": 108783360,
       "note": "SmolVLM 500M vision projector (SigLIP ~93M + MLP). Q8_0 quantized. Must be loaded alongside smolvlm_500m_q8_gguf."
+    },
+    "phi3_mini_q4_gguf": {
+      "kind": "model",
+      "framework": "llama.cpp-et",
+      "variant": "Phi-3-mini-4k-instruct-q4",
+      "filename": "Phi-3-mini-4k-instruct-q4.gguf",
+      "env": "PHI3_MINI_MODEL_PATH",
+      "source": {
+        "type": "huggingface",
+        "repo": "microsoft/Phi-3-mini-4k-instruct-gguf",
+        "revision": "main",
+        "filename": "Phi-3-mini-4k-instruct-q4.gguf",
+        "url": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf"
+      },
+      "sha256": "8a83c7fb9049a9b2e92266fa7ad04933bb53aa1e85136b7b30f1b8000ff2edef",
+      "size": 2393231072,
+      "local_cache": "local-artifacts/models/Phi-3-mini-4k-instruct-q4.gguf",
+      "board_path": "/data/models/Phi-3-mini-4k-instruct-q4.gguf"
+    },
+    "minicpm3_4b_q8_gguf": {
+      "kind": "model",
+      "framework": "llama.cpp-et",
+      "variant": "MiniCPM3-4B-Q8_0",
+      "filename": "MiniCPM3-4B-Q8_0.gguf",
+      "env": "MINICPM3_4B_MODEL_PATH",
+      "source": {
+        "type": "huggingface",
+        "repo": "QuantFactory/MiniCPM3-4B-GGUF",
+        "revision": "main",
+        "filename": "MiniCPM3-4B.Q8_0.gguf",
+        "url": "https://huggingface.co/QuantFactory/MiniCPM3-4B-GGUF/resolve/main/MiniCPM3-4B.Q8_0.gguf"
+      },
+      "sha256": "a540961f131d6ab9616b6cb1c266be86735afe84907a445ad68e1e3e9422d122",
+      "size": 4331349440,
+      "local_cache": "local-artifacts/models/MiniCPM3-4B-Q8_0.gguf",
+      "board_path": "/data/models/MiniCPM3-4B-Q8_0.gguf"
     }
   }
 }

ported_models/llama_cpp_et/benchmarks/minicpm3_4b.json

@@ -0,0 +1,52 @@
+{
+  "runner": "llama_server",
+  "board": true,
+  "framework": {
+    "name": "llama.cpp-et",
+    "runner": "llama_server",
+    "source_artifact": "llama_cpp_source"
+  },
+  "artifacts_file": "../artifacts.json",
+  "canonical_variant": "MiniCPM3-4B-Q8_0",
+  "score": {
+    "metric": "tokens_per_second",
+    "label": "Decode tokens/s",
+    "higher_is_better": true
+  },
+  "llama_server": {
+    "source_artifact": "llama_cpp_source",
+    "model_artifact": "minicpm3_4b_q8_gguf",
+    "server_artifact": "llama_server",
+    "workdir_artifact": "llama_cpp_build",
+    "host": "127.0.0.1",
+    "port": 18134,
+    "device": "ET",
+    "gpu_layers": 99,
+    "ctx_size": 2048,
+    "batch_size": 256,
+    "ubatch_size": 128,
+    "parallel": 1,
+    "cache_ram_mib": 0,
+    "ready_timeout_s": 300,
+    "request_timeout_s": 420,
+    "flash_attn": false,
+    "api": "completion",
+    "prompt": "Repeat this token sequence without commentary: OK OK OK OK OK OK OK OK OK OK",
+    "max_tokens": 96,
+    "temperature": 0,
+    "ignore_eos": true,
+    "min_completion_tokens": 32,
+    "perplexity": {
+      "enabled": true,
+      "perplexity_artifact": "llama_perplexity",
+      "corpus_artifact": "wikitext2_raw_test",
+      "ctx_size": 128,
+      "batch_size": 128,
+      "ubatch_size": 128,
+      "timeout_s": 420,
+      "min_ppl": 1.0,
+      "max_ppl": 1000.0,
+      "chunks": 4
+    }
+  }
+}

ported_models/llama_cpp_et/benchmarks/phi3_mini.json

@@ -0,0 +1,52 @@
+{
+  "runner": "llama_server",
+  "board": true,
+  "framework": {
+    "name": "llama.cpp-et",
+    "runner": "llama_server",
+    "source_artifact": "llama_cpp_source"
+  },
+  "artifacts_file": "../artifacts.json",
+  "canonical_variant": "Phi-3-mini-4k-instruct-q4",
+  "score": {
+    "metric": "tokens_per_second",
+    "label": "Decode tokens/s",
+    "higher_is_better": true
+  },
+  "llama_server": {
+    "source_artifact": "llama_cpp_source",
+    "model_artifact": "phi3_mini_q4_gguf",
+    "server_artifact": "llama_server",
+    "workdir_artifact": "llama_cpp_build",
+    "host": "127.0.0.1",
+    "port": 18133,
+    "device": "ET",
+    "gpu_layers": 99,
+    "ctx_size": 2048,
+    "batch_size": 256,
+    "ubatch_size": 128,
+    "parallel": 1,
+    "cache_ram_mib": 0,
+    "ready_timeout_s": 300,
+    "request_timeout_s": 420,
+    "flash_attn": false,
+    "api": "completion",
+    "prompt": "Repeat this token sequence without commentary: OK OK OK OK OK OK OK OK OK OK",
+    "max_tokens": 96,
+    "temperature": 0,
+    "ignore_eos": true,
+    "min_completion_tokens": 32,
+    "perplexity": {
+      "enabled": true,
+      "perplexity_artifact": "llama_perplexity",
+      "corpus_artifact": "wikitext2_raw_test",
+      "ctx_size": 128,
+      "batch_size": 128,
+      "ubatch_size": 128,
+      "timeout_s": 420,
+      "min_ppl": 1.0,
+      "max_ppl": 1000.0,
+      "chunks": 4
+    }
+  }
+}