| { |
| "schema_version": "5.1", |
| "name": "embeddinggemma-2-p150", |
| "tt_metal_version": "0.0.0.dev0", |
| "arch": "blackhole", |
| "device_count": 1, |
| "producer": { |
| "tt_kernel_version": "0.1.0", |
| "created_at": "2026-10-21T15:24:58.977613+00:00", |
| "hostname": "qb2-120-p06t08" |
| }, |
| "weights": { |
| "repo_id": "google/embeddinggemma-2", |
| "revision": "914f7f89142e33e77833254d9c9b90c3cef7303b", |
| "allow_patterns": null, |
| "ignore_patterns": null, |
| "repo_type": "model" |
| }, |
| "auxiliary_weights": [], |
| "mesh": null, |
| "entrypoint": null, |
| "resources": null, |
| "capabilities": null, |
| "env": {}, |
| "bundled": null, |
| "deps": null, |
| "container": { |
| "image": { |
| "registry": "hf", |
| "repository": "embeddinggemma-2-p150", |
| "tag": "tt-model/embeddinggemma-2-p150:0bd59b87edea", |
| "digest": "sha256:0bd59b87edea4b92e96656bdead06a361eac00643fecbca5a1a247c55a460fed" |
| }, |
| "kind": "tt-dit-server", |
| "runtime": { |
| "app": "models.autoports.google_embeddinggemma_2.server.app:app", |
| "lock": "requirements.lock", |
| "mesh_shape_env": "EMBEDDINGGEMMA_MESH_SHAPE" |
| }, |
| "serve": { |
| "hardware": "p150", |
| "mesh_device": "P150", |
| "port": null, |
| "max_model_len": null, |
| "max_num_seqs": null, |
| "block_size": null, |
| "server_timeout": null, |
| "capabilities": null, |
| "additional_config": {}, |
| "args": [], |
| "env": { |
| "HF_REVISION": "914f7f89142e33e77833254d9c9b90c3cef7303b", |
| "TT_MESH_GRAPH_DESC_PATH": "/opt/tt-metal/tt_metal/fabric/mesh_graph_descriptors/p150_mesh_graph_descriptor.textproto", |
| "EMBEDDINGGEMMA_ALLOW_URLS": "0" |
| } |
| }, |
| "serve_profiles": [ |
| { |
| "hardware": null, |
| "mesh_device": null, |
| "port": null, |
| "max_model_len": null, |
| "max_num_seqs": null, |
| "block_size": null, |
| "server_timeout": null, |
| "capabilities": null, |
| "additional_config": {}, |
| "args": [], |
| "env": {}, |
| "name": "default", |
| "description": "OpenAI-style /v1/embeddings server only." |
| }, |
| { |
| "hardware": null, |
| "mesh_device": null, |
| "port": null, |
| "max_model_len": null, |
| "max_num_seqs": null, |
| "block_size": null, |
| "server_timeout": null, |
| "capabilities": null, |
| "additional_config": {}, |
| "args": [], |
| "env": { |
| "EMBEDDINGGEMMA_DEMO": "1", |
| "EMBEDDINGGEMMA_DEMO_CACHE": "/tensor-cache/demo-index", |
| "GRADIO_ANALYTICS_ENABLED": "False" |
| }, |
| "name": "demo", |
| "description": "The /v1/embeddings server plus a Gradio demo at /demo (media, video moments, audio, code, multilingual and Matryoshka search over a bundled openly licensed library)." |
| } |
| ], |
| "default_profile": "default", |
| "code_dir": "code", |
| "verify": [ |
| "import os, stat; bad = [os.path.join(d, n) for d, ds, fs in os.walk('/opt/tt-metal/models') for n in ds + fs if not os.stat(os.path.join(d, n)).st_mode & stat.S_IROTH or (n in ds and not os.stat(os.path.join(d, n)).st_mode & stat.S_IXOTH)]; assert not bad, bad[:5]", |
| "import pathlib, models.autoports.google_embeddinggemma_2.tt.precision_policy as p; assert p.DEFAULT_PATH.is_file(), p.DEFAULT_PATH", |
| "import models.autoports.google_embeddinggemma_2.tt.custom_sdpa as s, models.autoports.google_embeddinggemma_2.tt.custom_geglu as g, pathlib; assert all(pathlib.Path(f).is_file() for f in (s.READER, s.WRITER, s.COMPUTE)); assert (g.KERNEL_DIR / 'compute.cpp').is_file()", |
| "import models.autoports.google_embeddinggemma_2.tt.embedder as e; assert e.supported_tokens() == 65536, e.supported_tokens()", |
| "import transformers, torch; assert transformers.__version__ == '5.12.1', transformers.__version__; assert torch.__version__ == '2.11.0+cpu', torch.__version__", |
| "from transformers.models.gemma4.feature_extraction_gemma4 import Gemma4AudioFeatureExtractor; from transformers.models.gemma4.image_processing_gemma4 import Gemma4ImageProcessor; import soundfile, orjson", |
| "import gradio, json, models.autoports.google_embeddinggemma_2.demo.ui as u, models.autoports.google_embeddinggemma_2.demo.index as i; assert gradio.__version__ == '6.30.0', gradio.__version__; m = json.loads((i.LIBRARY_DIR / 'manifest.json').read_text()); missing = [x['file'] for x in m['items'] if x.get('file') and not (i.LIBRARY_DIR / x['file']).is_file()]; assert not missing, missing[:5]" |
| ], |
| "built": { |
| "image": "tt-model/embeddinggemma-2-p150:0bd59b87edea", |
| "repo": "tt-hous/embeddinggemma-2", |
| "tt_model_version": "0.1.0", |
| "created_at": "2026-10-21T15:23:55+00:00", |
| "tt_metal": { |
| "sha": "3be67656b28e3902f0366ea8bab03c41e7e5bd6c", |
| "describe": null, |
| "dirty": false, |
| "scm_version": "0.0.0.dev0", |
| "mode": "git", |
| "remote": "https://github.com/tenstorrent/tt-metal.git", |
| "branch": null, |
| "pushed": null |
| }, |
| "code_sha256": "852ada085de3df458409d2183b853e843234bd60acff1efb98eb3c32c62dd77d", |
| "image_digest": "sha256:0bd59b87edea4b92e96656bdead06a361eac00643fecbca5a1a247c55a460fed" |
| }, |
| "card": { |
| "description": "EmbeddingGemma 2, a multimodal embedding model. Text, code, images, video frames and 16 kHz audio each map to one L2-normalized 768-dimensional vector in a shared space, so a text query can find an image, a sound or a video. Matryoshka dimensions 512, 256 and 128 are the first values of the 768-dimensional vector, re-normalized on the chip.\n\nThe text tower is a bidirectional 24-layer Gemma encoder (hidden size 512, sliding and full attention, 8192-token context). Gemma 4 vision (16 layers) and audio (12 layers) towers feed soft tokens into it. Weights stay on the chip and every request shape runs as a captured TTNN trace. Two custom kernels (sliding-window SDPA and a GEGLU matmul) run through stock `ttnn.generic_op`; tt-metal itself is unmodified.\n", |
| "attribution": "Derived from google/embeddinggemma-2 by Google DeepMind, weights unmodified. The TTNN port is models/autoports/google_embeddinggemma_2, on stock upstream tt-metal.\n", |
| "prerequisites": "- 1 GB hugepages mounted at `/dev/hugepages-1G`\n- One chip of a p300 also works: the package sets the p150 mesh graph descriptor.\n", |
| "quickstart": "### Embedding text\n```bash\ncurl -s localhost:20000/v1/embeddings -H 'content-type: application/json' \\\n -d '{\"input\": [\"What is the capital of France?\"], \"input_type\": \"query\", \"dimensions\": 256}'\n```\n\n### Demo\n```bash\ntt serve tt-hous/embeddinggemma-2 --profile demo\n```\nOpen `http://<host>:20000/demo/`. A web page where every query is embedded live on the chip, over a bundled library of 163 openly licensed images, videos, sounds, texts in 10 languages and code snippets: media search, finding a moment in a long video, audio search, code search, multilingual search, and a side-by-side Matryoshka comparison.\n", |
| "architecture": null, |
| "status": null, |
| "intended_use": "Embeddings for retrieval, semantic search, clustering and classification over text, code, images, video and audio, served from one p150. Not for generating text.\n", |
| "out_of_scope_use": null, |
| "usage": "`POST /v1/embeddings` follows the OpenAI embeddings request and response shapes, with media extensions.\n\n| field | meaning | default |\n|---|---|---|\n| `input` | a string, or a list of 1 to 2048 strings and media items | required |\n| `dimensions` | 768, 512, 256 or 128 | 768 |\n| `input_type` | a sentence-transformers prompt name, for example `query`, `document`, `CodeRetrieval` | no prompt |\n| `encoding_format` | `float`, or `base64` (little-endian float32) | `float` |\n| `model` | optional; `google/embeddinggemma-2` or `embeddinggemma-2` | |\n\nA media item is an object with optional `text` and at most one media field:\n\n| field | value |\n|---|---|\n| `image` | base64 image bytes (any PIL format) or a `data:image/...;base64,` URL |\n| `audio` | base64 16 kHz WAV; clips over 30 s are cut to 30 s |\n| `video` | `{\"frames\": [<base64 image>, ...], \"fps\": 1}`; at most 32 frames are used |\n\n```bash\nIMG=$(base64 -w0 cats.jpg)\ncurl -s localhost:20000/v1/embeddings -H 'content-type: application/json' \\\n -d \"{\\\"input\\\": [{\\\"image\\\": \\\"$IMG\\\"}, {\\\"text\\\": \\\"two cats on a couch\\\"}]}\"\n```\n\n`GET /health` answers 200 once the traces are captured, with the precision policy and live counters, and 503 before that. `GET /v1/models` lists the model, its dimensions and modalities. Errors use the OpenAI error shape; an input over 8192 tokens gets 400 `context_length_exceeded`. Media URLs are refused: send media as base64.\n", |
| "performance": "| benchmark (768d) | metric | this package | HF fp32 | card |\n| --- | --- | ---: | ---: | ---: |\n| MTEB multilingual v2 | Mean(Task) | 59.55 | 59.51 | 61.36 |\n| MTEB eng v2 | Mean(Task) | 70.25 | 70.35 | 68.46 |\n| MTEB code v1 | Mean(Task), NDCG@10 | 56.99 | 57.04 | 78.68 |\n| MIEB lite | Mean(TaskType) | 60.93 | 60.50 | 64.64 |\n| MMEB v2 Image | Mean(Task), Hit@1 | 38.85 | 39.10 | 57.28 |\n| MMEB v2 VisDoc | Mean(Task), NDCG@5 | 70.26 | 69.39 | 67.84 |\n| MMEB v2 Video | Mean(Task), Hit@1 | 20.09 | 19.63 | 50.67 |\n| MSEB Retrieval | Mean(Task), MRR@10 | 80.20 | 80.18 | 69.54 |\n| MAEB | Mean(Task) | 58.16 | 58.28 | 49.39 |\n\n| dimensions | storage | MTEB multilingual | MTEB eng | MTEB code | MIEB lite | MMEB overall | MSEB | MAEB |\n| ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |\n| 768 | 1x | 59.55 | 70.25 | 56.99 | 60.93 | 44.19 | 80.20 | 58.16 |\n| 512 | 1/1.5 | 59.20 | 70.24 | 56.62 | 60.77 | 44.70 | 78.99 | 57.93 |\n| 256 | 1/3 | 58.61 | 69.54 | 55.72 | 59.50 | 42.37 | 76.26 | 57.84 |\n| 128 | 1/6 | 55.76 | 67.90 | 52.30 | 55.57 | 37.12 | 60.25 | 55.25 |\n\n| load, one text of 480 to 512 tokens per request | requests/s | p50 (ms) | p99 (ms) |\n| --- | ---: | ---: | ---: |\n| 1 user | 88.5 | 11.4 | 13.1 |\n| 8 users | 207.7 | 38.5 | 40.5 |\n| 32 users | 277.3 | 114.1 | 122.3 |\n\n| single request, warm | latency (ms) |\n| --- | ---: |\n| text, 128 tokens | 5.8 |\n| text, 512 tokens | 7.7 |\n| text, 8192 tokens | 80.3 |\n| image | 47.8 |\n| video, 8 frames | 138.1 |\n| audio, 30 s | 32.2 |\n\nMeasured on one Blackhole chip of a p300c board opened as a 1x1 mesh (equal to a p150, compute grid 11x10), precision policy x02. Accuracy: a fixed subset of each benchmark, scored with the same inputs, prompts and code on this package and on the Hugging Face fp32 reference on CPU; \"card\" is the full-suite score from the google/embeddinggemma-2 card and is not comparable to subset means. No benchmark mean differs from HF fp32 by more than 1.0 point at any dimension. Load: a real server with closed-loop clients, 60 s per level, 0 errors. Single request: host staging, trace replay and readback, without tokenization or media decoding.\n", |
| "limitations": "- Bring-up build, not a Tenstorrent release.\n- One chip per server; no multi-chip mode.\n- At most 8192 tokens per input, counting the prompt and media tokens.\n- A vector depends slightly on the device batch it ran in (cosine down to 0.98 on hard inputs). Send one input per request for repeatable vectors.\n- Against HF fp32, 8 of the evaluation texts and 37 audio clips fall below 0.995 cosine (minimum 0.959); benchmark means still match within 1.0 point.\n- Audio must be 16 kHz WAV and is cut to 30 s. Video arrives as decoded frames, at most 32. Images use the default 280-token budget.\n- Never run in fp16: the base model card warns it gives NaN or degraded vectors.\n- The first boot compiles kernels and captures 51 traces (about 6 minutes); later boots take about 30 s.\n- Validated on one chip of a p300c. Performance on a p150 with a larger compute grid was not measured.\n", |
| "risks": null, |
| "licensing": "Weights under the upstream Apache-2.0 licence (google/embeddinggemma-2). The TTNN port and the server in `code/` are Apache-2.0 (tt-metal). Demo library items carry their own CC0, public domain, CC BY, CC BY-SA, Apache-2.0 or MIT licences, listed in `code/models/autoports/google_embeddinggemma_2/demo/library/LICENSES.md`.\n", |
| "related": null, |
| "license": { |
| "id": "apache-2.0", |
| "name": null, |
| "link": null |
| }, |
| "pipeline_tag": "feature-extraction", |
| "base_model": [ |
| "google/embeddinggemma-2" |
| ] |
| } |
| } |
| } |
