Hugging Face's logo

executorch-community
/
SmolVLM-500M-Instruct-ExecuTorch-WebGPU

Image-Text-to-Text
ExecuTorch
webgpu
on-device
browser
Model card Files
xet
 Community
SmolVLM-500M-Instruct-ExecuTorch-WebGPU / export /recipe.json
psiddh's picture
psiddh
Add ExecuTorch WebGPU program for smolvlm-500m-instruct
86276a1 verified
Raw History Blame Contribute Delete
75.8 kB
{
"model": "smolvlm-500m-instruct-q8",
"variant": "q8",
"upstream": {
"model": "HuggingFaceTB/SmolVLM-500M-Instruct",
"revision": "a7da5b986cb59b408707209984f360a5f4ad7e47",
"official": true,
"sha256": {
"model.safetensors": "d05b567eeaf534e83d375551f068ed57b5f52d37c657197f644af5ef9db091a2",
"config.json": "daacbbca6af3c34e50466c72aed2df4553a08084f6a0551d4ae420a241cb66c6",
"generation_config.json": "067a2a54e5f87162ecac6e0e911cc4665fc8f7f3324794ecbac0f76badb56636",
"preprocessor_config.json": "6cb6e36d6fcb88ca1502c4a26750715dc3e7dedddc9a8f17b27d8d167d1457e7",
"tokenizer.json": "5ece781dc8d2b2f3e2f289ca0ae50b17cfc27dd27bfe7971bb8241e0b964331a",
"tokenizer_config.json": "36c6fd44d07d10fd8180ee6b46dcccf69fb7c06753968ff0d7e17b8bfe17b777",
"special_tokens_map.json": "aa0ff906077086dfa9734a7f97f68c825877a48f9468807be65504495cdeef09"
}
},
"versions": {
"python": "3.12.15+meta",
"torch": "2.14.1+cpu",
"torchao": "0.18.0+cpu",
"executorch": "1.5.1+cpu",
"executorch_git": "3b60683923245cf472b7323426920e15623ba361",
"transformers": "5.19.0",
"huggingface_hub": "2.2.0"
},
"export": {
"partitioner": "executorch.backends.webgpu.partitioner.WebGPUPartitioner, default options (static shapes)",
"linear": "et_vk.linear_q8ta_q8csw: int8 activations, one static per-tensor affine scale per pass (torchao MinMaxObserver over the calibration data, [-128, 127]); int8 weights, per-output-channel symmetric (VulkanQuantizer weight spec, scale amax/127.5)",
"export_workaround": "_smolvlm_q8.fix_q8ta_fake(): a fake kernel giving et_vk.linear_q8ta_q8csw its real fp32 output dtype during lowering (executorch 1.5.1's reference kernel reports int8, which breaks llama::custom_sdpa's meta check and would mis-declare tensors). Metadata only",
"programs": {
"smolvlm_vision_q8.pte": {
"api": "torch.export.export(strict=False) -> to_edge_transform_and_lower(partitioner=[WebGPUPartitioner()]) -> to_executorch()",
"module": "transformers Idefics3 vision tower (eager attention) + post_layernorm + connector; identity position ids for a full 512x512 image",
"inputs": [
{
"name": "pixel_values",
"shape": [
1,
3,
512,
512
],
"dtype": "float32",
"range": "(x/255 - 0.5)/0.5"
}
],
"outputs": [
{
"name": "image_embeds",
"shape": [
1,
64,
960
],
"dtype": "float32"
}
],
"quantization": "all 73 linears 8-bit, two passes (second pass on the first pass's rounding error, same int8 weight), weights GPTQ (damp 0.01, block 128, float64) on the calibration inputs, same grid (the connector, with fewer calibration rows than inputs, round to nearest); patch embedding conv, layer norms, position table fp32"
},
"smolvlm_decoder_q8.pte": {
"api": "LLMEdgeManager: export(strict) -> run_canonical_optimizations -> export_to_edge -> to_backend([WebGPUPartitioner()]) -> to_executorch; static shapes",
"module": "executorch examples/models/llama Transformer (apply_embedding=False, use_hf_rope, enable_dynamic_shape for the start position) with weights from executorch.examples.models.smolvlm.convert_weights; source transforms from export_llama_lib._get_source_transforms(use_sdpa_with_kv_cache, use_kv_cache)",
"params": {
"dim": 960,
"hidden_dim": 2560,
"n_heads": 15,
"n_kv_heads": 5,
"head_dim": 64,
"n_layers": 32,
"norm_eps": 1e-05,
"rope_theta": 100000.0,
"use_scaled_rope": false,
"use_hf_rope": true,
"attention_qkv_bias": false,
"vocab_size": 49280,
"apply_embedding": false
},
"inputs": [
{
"name": "embeds",
"shape": [
1,
4,
960
],
"dtype": "float32",
"note": "rows of positions input_pos .. input_pos + rows - 1"
},
{
"name": "input_pos",
"shape": [
1
],
"dtype": "int64",
"note": "position of the first row"
}
],
"outputs": [
{
"name": "logits",
"shape": [
1,
49280
],
"dtype": "float32",
"note": "last row only"
}
],
"kv_cache": "in the program: 32 layers x k/v [1,512,5,64] fp32; every call writes its rows' positions",
"attention_sink": "position 0 must be <|im_start|> (id 1), as the chat template always starts: its per-layer K/V (fp32 model, int8-table embedding row) are constants the program writes over row 0 when input_pos is 0; that row is excluded from calibration",
"host_contract": "feed positions in windows of `rows` rows ending at the newest position (window_starts in _smolvlm_q8.py / windowStarts in vlm.js); input_pos + rows <= max_context",
"max_context_length": 512,
"quantization": "all 225 linears incl. lm_head 8-bit, two passes (second pass on the first pass's rounding error, same int8 weight), weights GPTQ (damp 0.01, block 128, float64) on the calibration inputs, same grid; RMSNorm weights fp32"
}
},
"calibration": {
"pairs": [
{
"image": "yolo_cat.jpg",
"image_sha256": "88b9eb3e6ec026c5ab96aab516f4a4a2773522a474abc52e934a52d86bba21e5",
"question": "What animal is this?",
"rows": 85,
"continuation": " This is a cat."
},
{
"image": "yolo_people.jpg",
"image_sha256": "16d73869e3267a7d4ed00de8e860833bd1657c1b252e94c0c348277adc7b6edb",
"question": "Describe this image",
"rows": 110,
"continuation": " The image depicts two men standing on a field, likely during a sports event or a public gathering. The men are dressed in formal attire, suggesting that they might"
},
{
"image": "yolo_street.jpg",
"image_sha256": "c02019c4979c191eb739ddd944445ef408dad5679acab6fd520ef9d434bfbc63",
"question": "What vehicles can you see?",
"rows": 88,
"continuation": " There are buses in the image."
},
{
"image": "yolo_table.jpg",
"image_sha256": "0ef0c3f7caa3ad4ec92dc8968f9ac0e81ede5b4805aae89648a4c7c4236768df",
"question": "What objects are on the table?",
"rows": 110,
"continuation": " There are cups, saucers, a cup with coffee, a bowl with pastries, and a plate with a napkin on the table."
},
{
"image": "sample_shapes.jpg",
"image_sha256": "f7911a973ef5a6dc962b92349f65a34f33b15e4c078052f8166018fe8338e074",
"question": "What shapes are in this picture?",
"rows": 114,
"continuation": " The image contains four distinct geometric shapes. Here is a detailed description of each shape:\n\n1. **Red Triangle**: Located on the left side of the image"
},
{
"image": "chihuahuas.jpg",
"image_sha256": "6f18287a5728ce32e3714b28a971f5c62d57e2cf0f689786611d438d5d7b7522",
"question": "How many dogs are there?",
"rows": 89,
"continuation": " There are two dogs in the image."
},
{
"image": "kitchen.jpg",
"image_sha256": "dbecca629f4ebe4c6d311c07f55de921bd77d32d6c85ab32e7a8033175556580",
"question": "Describe this image",
"rows": 110,
"continuation": " A kitchen with a large island in the center, which has a granite countertop and a sink with a double faucet. There are two large bowls on the island"
},
{
"image": "giraffes.jpg",
"image_sha256": "e10d0f49a1e3b0d01bb6186bf59ca25a2c310a8d7d8ca7781eec76313ccc4ea1",
"question": "What is happening here?",
"rows": 88,
"continuation": " There are giraffes walking in the field."
}
],
"continuation_tokens": 32,
"decoder_windows": "4 rows, the browser's window plan",
"vision": "the 8 calibration images"
},
"activation_qparams": {
"vision": {
"layers.0.self_attn.k_proj": [
[
0.11057502031326294,
0
],
[
0.00043362739961594343,
-1
]
],
"layers.0.self_attn.v_proj": [
[
0.11057502031326294,
0
],
[
0.00043362739961594343,
-1
]
],
"layers.0.self_attn.q_proj": [
[
0.11057502031326294,
0
],
[
0.00043362739961594343,
-1
]
],
"layers.0.self_attn.out_proj": [
[
0.03311925381422043,
9
],
[
0.00012987936497665942,
-1
]
],
"layers.0.mlp.fc1": [
[
0.29603707790374756,
3
],
[
0.0011609295615926385,
-1
]
],
"layers.0.mlp.fc2": [
[
0.04607229679822922,
-124
],
[
0.00018067570636048913,
0
]
],
"layers.1.self_attn.k_proj": [
[
0.11797387152910233,
-7
],
[
0.00046264249249361455,
0
]
],
"layers.1.self_attn.v_proj": [
[
0.11797387152910233,
-7
],
[
0.00046264249249361455,
0
]
],
"layers.1.self_attn.q_proj": [
[
0.11797387152910233,
-7
],
[
0.00046264249249361455,
0
]
],
"layers.1.self_attn.out_proj": [
[
0.025301799178123474,
5
],
[
9.922267781803384e-05,
0
]
],
"layers.1.mlp.fc1": [
[
0.15761414170265198,
-11
],
[
0.0006180948112159967,
-1
]
],
"layers.1.mlp.fc2": [
[
0.021325966343283653,
-120
],
[
8.363127562915906e-05,
0
]
],
"layers.2.self_attn.k_proj": [
[
0.18797777593135834,
-25
],
[
0.0007371677202172577,
-1
]
],
"layers.2.self_attn.v_proj": [
[
0.18797777593135834,
-25
],
[
0.0007371677202172577,
-1
]
],
"layers.2.self_attn.q_proj": [
[
0.18797777593135834,
-25
],
[
0.0007371677202172577,
-1
]
],
"layers.2.self_attn.out_proj": [
[
0.02796168625354767,
-9
],
[
0.0001096536434488371,
-1
]
],
"layers.2.mlp.fc1": [
[
0.15474054217338562,
-36
],
[
0.0006068257498554885,
0
]
],
"layers.2.mlp.fc2": [
[
0.019050095230340958,
-119
],
[
7.470636046491563e-05,
-1
]
],
"layers.3.self_attn.k_proj": [
[
0.18854397535324097,
-16
],
[
0.0007393882842734456,
-1
]
],
"layers.3.self_attn.v_proj": [
[
0.18854397535324097,
-16
],
[
0.0007393882842734456,
-1
]
],
"layers.3.self_attn.q_proj": [
[
0.18854397535324097,
-16
],
[
0.0007393882842734456,
-1
]
],
"layers.3.self_attn.out_proj": [
[
0.028024116531014442,
26
],
[
0.00010989848669851199,
-1
]
],
"layers.3.mlp.fc1": [
[
0.1748019903898239,
-28
],
[
0.0006854981184005737,
-1
]
],
"layers.3.mlp.fc2": [
[
0.021401548758149147,
-120
],
[
8.392766176257282e-05,
0
]
],
"layers.4.self_attn.k_proj": [
[
0.2204122543334961,
-24
],
[
0.0008643616456538439,
0
]
],
"layers.4.self_attn.v_proj": [
[
0.2204122543334961,
-24
],
[
0.0008643616456538439,
0
]
],
"layers.4.self_attn.q_proj": [
[
0.2204122543334961,
-24
],
[
0.0008643616456538439,
0
]
],
"layers.4.self_attn.out_proj": [
[
0.026799356564879417,
5
],
[
0.00010509543790249154,
0
]
],
"layers.4.mlp.fc1": [
[
0.21318072080612183,
-15
],
[
0.000836003280710429,
0
]
],
"layers.4.mlp.fc2": [
[
0.03725965693593025,
-123
],
[
0.00014611640654038638,
0
]
],
"layers.5.self_attn.k_proj": [
[
0.1860852837562561,
-7
],
[
0.0007297461852431297,
-1
]
],
"layers.5.self_attn.v_proj": [
[
0.1860852837562561,
-7
],
[
0.0007297461852431297,
-1
]
],
"layers.5.self_attn.q_proj": [
[
0.1860852837562561,
-7
],
[
0.0007297461852431297,
-1
]
],
"layers.5.self_attn.out_proj": [
[
0.03250356763601303,
21
],
[
0.00012746502761729062,
0
]
],
"layers.5.mlp.fc1": [
[
0.22218218445777893,
-6
],
[
0.0008713023853488266,
-1
]
],
"layers.5.mlp.fc2": [
[
0.12603624165058136,
-127
],
[
0.0004942595842294395,
0
]
],
"layers.6.self_attn.k_proj": [
[
0.20868107676506042,
-1
],
[
0.000818357162643224,
0
]
],
"layers.6.self_attn.v_proj": [
[
0.20868107676506042,
-1
],
[
0.000818357162643224,
0
]
],
"layers.6.self_attn.q_proj": [
[
0.20868107676506042,
-1
],
[
0.000818357162643224,
0
]
],
"layers.6.self_attn.out_proj": [
[
0.028652627021074295,
6
],
[
0.00011236334830755368,
-1
]
],
"layers.6.mlp.fc1": [
[
0.18634845316410065,
8
],
[
0.0007307780906558037,
0
]
],
"layers.6.mlp.fc2": [
[
0.04141681641340256,
-124
],
[
0.00016241887351498008,
0
]
],
"layers.7.self_attn.k_proj": [
[
0.19424130022525787,
7
],
[
0.00076173065463081,
-1
]
],
"layers.7.self_attn.v_proj": [
[
0.19424130022525787,
7
],
[
0.00076173065463081,
-1
]
],
"layers.7.self_attn.q_proj": [
[
0.19424130022525787,
7
],
[
0.00076173065463081,
-1
]
],
"layers.7.self_attn.out_proj": [
[
0.025726741179823875,
-21
],
[
0.00010088913404615596,
0
]
],
"layers.7.mlp.fc1": [
[
0.18025848269462585,
27
],
[
0.0007068958948366344,
0
]
],
"layers.7.mlp.fc2": [
[
0.0317450687289238,
-123
],
[
0.0001244904997292906,
-1
]
],
"layers.8.self_attn.k_proj": [
[
0.2215735763311386,
19
],
[
0.0008689158130437136,
-1
]
],
"layers.8.self_attn.v_proj": [
[
0.2215735763311386,
19
],
[
0.0008689158130437136,
-1
]
],
"layers.8.self_attn.q_proj": [
[
0.2215735763311386,
19
],
[
0.0008689158130437136,
-1
]
],
"layers.8.self_attn.out_proj": [
[
0.03458048775792122,
20
],
[
0.00013560972001869231,
0
]
],
"layers.8.mlp.fc1": [
[
0.18420721590518951,
17
],
[
0.000722382334060967,
-1
]
],
"layers.8.mlp.fc2": [
[
0.028086207807064056,
-122
],
[
0.0001101423695217818,
-1
]
],
"layers.9.self_attn.k_proj": [
[
0.24290066957473755,
31
],
[
0.000952551665250212,
0
]
],
"layers.9.self_attn.v_proj": [
[
0.24290066957473755,
31
],
[
0.000952551665250212,
0
]
],
"layers.9.self_attn.q_proj": [
[
0.24290066957473755,
31
],
[
0.000952551665250212,
0
]
],
"layers.9.self_attn.out_proj": [
[
0.03084946796298027,
10
],
[
0.00012097826402168721,
0
]
],
"layers.9.mlp.fc1": [
[
0.3155311346054077,
-4
],
[
0.0012373793870210648,
-1
]
],
"layers.9.mlp.fc2": [
[
0.06736534833908081,
-125
],
[
0.0002641777682583779,
0
]
],
"layers.10.self_attn.k_proj": [
[
0.2827392816543579,
33
],
[
0.0011087822495028377,
0
]
],
"layers.10.self_attn.v_proj": [
[
0.2827392816543579,
33
],
[
0.0011087822495028377,
0
]
],
"layers.10.self_attn.q_proj": [
[
0.2827392816543579,
33
],
[
0.0011087822495028377,
0
]
],
"layers.10.self_attn.out_proj": [
[
0.02676890231668949,
10
],
[
0.00010497611219761893,
-1
]
],
"layers.10.mlp.fc1": [
[
0.6608939170837402,
-3
],
[
0.002591740805655718,
0
]
],
"layers.10.mlp.fc2": [
[
0.11313328146934509,
-126
],
[
0.0004436599847394973,
0
]
],
"layers.11.self_attn.k_proj": [
[
0.29342105984687805,
23
],
[
0.0011506739538162947,
-1
]
],
"layers.11.self_attn.v_proj": [
[
0.29342105984687805,
23
],
[
0.0011506739538162947,
-1
]
],
"layers.11.self_attn.q_proj": [
[
0.29342105984687805,
23
],
[
0.0011506739538162947,
-1
]
],
"layers.11.self_attn.out_proj": [
[
0.03917478024959564,
-11
],
[
0.00015362711565103382,
0
]
],
"layers.11.mlp.fc1": [
[
0.5828185081481934,
-9
],
[
0.002285564551129937,
0
]
],
"layers.11.mlp.fc2": [
[
0.42501285672187805,
-128
],
[
0.0016667165327817202,
0
]
],
"connector.modality_projection.proj": [
[
0.18216344714164734,
19
],
[
0.000714366149622947,
-1
]
]
},
"decoder": {
"layers.0.attention.wq": [
[
0.017823828384280205,
40
],
[
6.989705434534699e-05,
0
]
],
"layers.0.attention.wk": [
[
0.017823828384280205,
40
],
[
6.989705434534699e-05,
0
]
],
"layers.0.attention.wv": [
[
0.017823828384280205,
40
],
[
6.989705434534699e-05,
0
]
],
"layers.0.attention.wo": [
[
0.007807944901287556,
-40
],
[
3.0619306926382706e-05,
0
]
],
"layers.0.feed_forward.w1": [
[
0.08885412663221359,
-112
],
[
0.000348444766132161,
0
]
],
"layers.0.feed_forward.w2": [
[
0.04989893361926079,
8
],
[
0.0001956819323822856,
-1
]
],
"layers.0.feed_forward.w3": [
[
0.08885412663221359,
-112
],
[
0.000348444766132161,
0
]
],
"layers.1.attention.wq": [
[
0.035501036792993546,
53
],
[
0.000139219468110241,
-1
]
],
"layers.1.attention.wk": [
[
0.035501036792993546,
53
],
[
0.000139219468110241,
-1
]
],
"layers.1.attention.wv": [
[
0.035501036792993546,
53
],
[
0.000139219468110241,
-1
]
],
"layers.1.attention.wo": [
[
0.019016792997717857,
-27
],
[
7.457551691913977e-05,
-1
]
],
"layers.1.feed_forward.w1": [
[
0.008405232802033424,
6
],
[
3.296163777122274e-05,
-1
]
],
"layers.1.feed_forward.w2": [
[
0.040298622101545334,
29
],
[
0.00015803368296474218,
-1
]
],
"layers.1.feed_forward.w3": [
[
0.008405232802033424,
6
],
[
3.296163777122274e-05,
-1
]
],
"layers.2.attention.wq": [
[
0.03276512399315834,
8
],
[
0.00012849035556428134,
-1
]
],
"layers.2.attention.wk": [
[
0.03276512399315834,
8
],
[
0.00012849035556428134,
-1
]
],
"layers.2.attention.wv": [
[
0.03276512399315834,
8
],
[
0.00012849035556428134,
-1
]
],
"layers.2.attention.wo": [
[
0.011804603971540928,
-4
],
[
4.6292545448523015e-05,
-1
]
],
"layers.2.feed_forward.w1": [
[
0.010259619913995266,
-1
],
[
4.0233793697552755e-05,
0
]
],
"layers.2.feed_forward.w2": [
[
0.0317905955016613,
-17
],
[
0.00012466894986573607,
0
]
],
"layers.2.feed_forward.w3": [
[
0.010259619913995266,
-1
],
[
4.0233793697552755e-05,
0
]
],
"layers.3.attention.wq": [
[
0.03699791058897972,
-2
],
[
0.00014508973981719464,
0
]
],
"layers.3.attention.wk": [
[
0.03699791058897972,
-2
],
[
0.00014508973981719464,
0
]
],
"layers.3.attention.wv": [
[
0.03699791058897972,
-2
],
[
0.00014508973981719464,
0
]
],
"layers.3.attention.wo": [
[
0.021720269694924355,
32
],
[
8.517743117408827e-05,
0
]
],
"layers.3.feed_forward.w1": [
[
0.014318770729005337,
-17
],
[
5.615192276309244e-05,
0
]
],
"layers.3.feed_forward.w2": [
[
0.33642786741256714,
-104
],
[
0.001319324248470366,
0
]
],
"layers.3.feed_forward.w3": [
[
0.014318770729005337,
-17
],
[
5.615192276309244e-05,
0
]
],
"layers.4.attention.wq": [
[
0.0462617389857769,
25
],
[
0.00018141795590054244,
0
]
],
"layers.4.attention.wk": [
[
0.0462617389857769,
25
],
[
0.00018141795590054244,
0
]
],
"layers.4.attention.wv": [
[
0.0462617389857769,
25
],
[
0.00018141795590054244,
0
]
],
"layers.4.attention.wo": [
[
0.01729913242161274,
2
],
[
6.783962453482673e-05,
0
]
],
"layers.4.feed_forward.w1": [
[
0.015150951221585274,
-27
],
[
5.9415444411570206e-05,
0
]
],
"layers.4.feed_forward.w2": [
[
0.04258466139435768,
15
],
[
0.00016699809930287302,
-1
]
],
"layers.4.feed_forward.w3": [
[
0.015150951221585274,
-27
],
[
5.9415444411570206e-05,
0
]
],
"layers.5.attention.wq": [
[
0.04702253267168999,
17
],
[
0.00018440181156620383,
0
]
],
"layers.5.attention.wk": [
[
0.04702253267168999,
17
],
[
0.00018440181156620383,
0
]
],
"layers.5.attention.wv": [
[
0.04702253267168999,
17
],
[
0.00018440181156620383,
0
]
],
"layers.5.attention.wo": [
[
0.015384010970592499,
-16
],
[
6.032934470567852e-05,
0
]
],
"layers.5.feed_forward.w1": [
[
0.012542051263153553,
-31
],
[
4.9184363888343796e-05,
0
]
],
"layers.5.feed_forward.w2": [
[
0.0316687673330307,
-13
],
[
0.00012419100676197559,
-1
]
],
"layers.5.feed_forward.w3": [
[
0.012542051263153553,
-31
],
[
4.9184363888343796e-05,
0
]
],
"layers.6.attention.wq": [
[
0.053652409464120865,
20
],
[
0.00021040139836259186,
0
]
],
"layers.6.attention.wk": [
[
0.053652409464120865,
20
],
[
0.00021040139836259186,
0
]
],
"layers.6.attention.wv": [
[
0.053652409464120865,
20
],
[
0.00021040139836259186,
0
]
],
"layers.6.attention.wo": [
[
0.016384968534111977,
-14
],
[
6.425465835491195e-05,
-1
]
],
"layers.6.feed_forward.w1": [
[
0.013905930332839489,
-22
],
[
5.453297490021214e-05,
-1
]
],
"layers.6.feed_forward.w2": [
[
0.06569673120975494,
-7
],
[
0.000257634004810825,
0
]
],
"layers.6.feed_forward.w3": [
[
0.013905930332839489,
-22
],
[
5.453297490021214e-05,
-1
]
],
"layers.7.attention.wq": [
[
0.048247963190078735,
20
],
[
0.00018920755246654153,
0
]
],
"layers.7.attention.wk": [
[
0.048247963190078735,
20
],
[
0.00018920755246654153,
0
]
],
"layers.7.attention.wv": [
[
0.048247963190078735,
20
],
[
0.00018920755246654153,
0
]
],
"layers.7.attention.wo": [
[
0.01625002734363079,
-19
],
[
6.372541247401386e-05,
0
]
],
"layers.7.feed_forward.w1": [
[
0.013832789845764637,
-6
],
[
5.424611299531534e-05,
-1
]
],
"layers.7.feed_forward.w2": [
[
0.055258866399526596,
-3
],
[
0.00021670118439942598,
-1
]
],
"layers.7.feed_forward.w3": [
[
0.013832789845764637,
-6
],
[
5.424611299531534e-05,
-1
]
],
"layers.8.attention.wq": [
[
0.046826478093862534,
25
],
[
0.0001836329756770283,
-1
]
],
"layers.8.attention.wk": [
[
0.046826478093862534,
25
],
[
0.0001836329756770283,
-1
]
],
"layers.8.attention.wv": [
[
0.046826478093862534,
25
],
[
0.0001836329756770283,
-1
]
],
"layers.8.attention.wo": [
[
0.020178530365228653,
6
],
[
7.91311904322356e-05,
0
]
],
"layers.8.feed_forward.w1": [
[
0.015370944514870644,
-26
],
[
6.0277943703113124e-05,
0
]
],
"layers.8.feed_forward.w2": [
[
0.06391426175832748,
34
],
[
0.0002506438468117267,
0
]
],
"layers.8.feed_forward.w3": [
[
0.015370944514870644,
-26
],
[
6.0277943703113124e-05,
0
]
],
"layers.9.attention.wq": [
[
0.05844179913401604,
14
],
[
0.00022918317699804902,
-1
]
],
"layers.9.attention.wk": [
[
0.05844179913401604,
14
],
[
0.00022918317699804902,
-1
]
],
"layers.9.attention.wv": [
[
0.05844179913401604,
14
],
[
0.00022918317699804902,
-1
]
],
"layers.9.attention.wo": [
[
0.020972328260540962,
-10
],
[
8.224398334277794e-05,
-1
]
],
"layers.9.feed_forward.w1": [
[
0.01582447625696659,
-30
],
[
6.205654062796384e-05,
-1
]
],
"layers.9.feed_forward.w2": [
[
0.061518240720033646,
-41
],
[
0.00024124795163515955,
-1
]
],
"layers.9.feed_forward.w3": [
[
0.01582447625696659,
-30
],
[
6.205654062796384e-05,
-1
]
],
"layers.10.attention.wq": [
[
0.057099029421806335,
13
],
[
0.00022391745005734265,
0
]
],
"layers.10.attention.wk": [
[
0.057099029421806335,
13
],
[
0.00022391745005734265,
0
]
],
"layers.10.attention.wv": [
[
0.057099029421806335,
13
],
[
0.00022391745005734265,
0
]
],
"layers.10.attention.wo": [
[
0.02361183613538742,
25
],
[
9.259540820494294e-05,
-1
]
],
"layers.10.feed_forward.w1": [
[
0.015977581962943077,
-31
],
[
6.265722186071798e-05,
0
]
],
"layers.10.feed_forward.w2": [
[
0.05527188628911972,
-12
],
[
0.000216752290725708,
0
]
],
"layers.10.feed_forward.w3": [
[
0.015977581962943077,
-31
],
[
6.265722186071798e-05,
0
]
],
"layers.11.attention.wq": [
[
0.05523655563592911,
18
],
[
0.0002166134217986837,
0
]
],
"layers.11.attention.wk": [
[
0.05523655563592911,
18
],
[
0.0002166134217986837,
0
]
],
"layers.11.attention.wv": [
[
0.05523655563592911,
18
],
[
0.0002166134217986837,
0
]
],
"layers.11.attention.wo": [
[
0.02736421301960945,
-27
],
[
0.000107310559542384,
0
]
],
"layers.11.feed_forward.w1": [
[
0.022182175889611244,
-12
],
[
8.698877354618162e-05,
-1
]
],
"layers.11.feed_forward.w2": [
[
0.048375293612480164,
-32
],
[
0.00018970677047036588,
-1
]
],
"layers.11.feed_forward.w3": [
[
0.022182175889611244,
-12
],
[
8.698877354618162e-05,
-1
]
],
"layers.12.attention.wq": [
[
0.060529887676239014,
17
],
[
0.00023737164156045765,
-1
]
],
"layers.12.attention.wk": [
[
0.060529887676239014,
17
],
[
0.00023737164156045765,
-1
]
],
"layers.12.attention.wv": [
[
0.060529887676239014,
17
],
[
0.00023737164156045765,
-1
]
],
"layers.12.attention.wo": [
[
0.024945423007011414,
-17
],
[
9.782514098333195e-05,
-1
]
],
"layers.12.feed_forward.w1": [
[
0.02477002516388893,
-32
],
[
9.713695908430964e-05,
0
]
],
"layers.12.feed_forward.w2": [
[
0.03289053589105606,
-7
],
[
0.00012898237037006766,
-1
]
],
"layers.12.feed_forward.w3": [
[
0.02477002516388893,
-32
],
[
9.713695908430964e-05,
0
]
],
"layers.13.attention.wq": [
[
0.06709799915552139,
18
],
[
0.00026312837144359946,
0
]
],
"layers.13.attention.wk": [
[
0.06709799915552139,
18
],
[
0.00026312837144359946,
0
]
],
"layers.13.attention.wv": [
[
0.06709799915552139,
18
],
[
0.00026312837144359946,
0
]
],
"layers.13.attention.wo": [
[
0.02714546211063862,
-8
],
[
0.00010645274596754462,
-1
]
],
"layers.13.feed_forward.w1": [
[
0.0362023301422596,
-55
],
[
0.00014196964912116528,
-1
]
],
"layers.13.feed_forward.w2": [
[
0.29110389947891235,
-97
],
[
0.0011415830813348293,
-1
]
],
"layers.13.feed_forward.w3": [
[
0.0362023301422596,
-55
],
[
0.00014196964912116528,
-1
]
],
"layers.14.attention.wq": [
[
0.06070156395435333,
20
],
[
0.0002380445512244478,
-1
]
],
"layers.14.attention.wk": [
[
0.06070156395435333,
20
],
[
0.0002380445512244478,
-1
]
],
"layers.14.attention.wv": [
[
0.06070156395435333,
20
],
[
0.0002380445512244478,
-1
]
],
"layers.14.attention.wo": [
[
0.02148558758199215,
-7
],
[
8.425699343206361e-05,
0
]
],
"layers.14.feed_forward.w1": [
[
0.016782715916633606,
15
],
[
6.581440538866445e-05,
-1
]
],
"layers.14.feed_forward.w2": [
[
0.036045271903276443,
-1
],
[
0.00014135372475720942,
0
]
],
"layers.14.feed_forward.w3": [
[
0.016782715916633606,
15
],
[
6.581440538866445e-05,
-1
]
],
"layers.15.attention.wq": [
[
0.052386704832315445,
26
],
[
0.00020543771097436547,
-1
]
],
"layers.15.attention.wk": [
[
0.052386704832315445,
26
],
[
0.00020543771097436547,
-1
]
],
"layers.15.attention.wv": [
[
0.052386704832315445,
26
],
[
0.00020543771097436547,
-1
]
],
"layers.15.attention.wo": [
[
0.02741842530667782,
10
],
[
0.00010752306843642145,
0
]
],
"layers.15.feed_forward.w1": [
[
0.016052227467298508,
13
],
[
6.294966442510486e-05,
-1
]
],
"layers.15.feed_forward.w2": [
[
0.036300696432590485,
-10
],
[
0.0001423554349457845,
0
]
],
"layers.15.feed_forward.w3": [
[
0.016052227467298508,
13
],
[
6.294966442510486e-05,
-1
]
],
"layers.16.attention.wq": [
[
0.057359110563993454,
24
],
[
0.00022493749565910548,
-1
]
],
"layers.16.attention.wk": [
[
0.057359110563993454,
24
],
[
0.00022493749565910548,
-1
]
],
"layers.16.attention.wv": [
[
0.057359110563993454,
24
],
[
0.00022493749565910548,
-1
]
],
"layers.16.attention.wo": [
[
0.022664036601781845,
-4
],
[
8.887828153092414e-05,
-1
]
],
"layers.16.feed_forward.w1": [
[
0.015661122277379036,
21
],
[
6.141592893982306e-05,
0
]
],
"layers.16.feed_forward.w2": [
[
0.029099423438310623,
9
],
[
0.0001141151660704054,
-1
]
],
"layers.16.feed_forward.w3": [
[
0.015661122277379036,
21
],
[
6.141592893982306e-05,
0
]
],
"layers.17.attention.wq": [
[
0.06801969558000565,
22
],
[
0.00026674376567825675,
-1
]
],
"layers.17.attention.wk": [
[
0.06801969558000565,
22
],
[
0.00026674376567825675,
-1
]
],
"layers.17.attention.wv": [
[
0.06801969558000565,
22
],
[
0.00026674376567825675,
-1
]
],
"layers.17.attention.wo": [
[
0.03552840277552605,
-11
],
[
0.00013932664296589792,
0
]
],
"layers.17.feed_forward.w1": [
[
0.016431303694844246,
16
],
[
6.443633901653811e-05,
-1
]
],
"layers.17.feed_forward.w2": [
[
0.03217285871505737,
6
],
[
0.00012616798630915582,
0
]
],
"layers.17.feed_forward.w3": [
[
0.016431303694844246,
16
],
[
6.443633901653811e-05,
-1
]
],
"layers.18.attention.wq": [
[
0.059997912496328354,
22
],
[
0.00023528531892225146,
0
]
],
"layers.18.attention.wk": [
[
0.059997912496328354,
22
],
[
0.00023528531892225146,
0
]
],
"layers.18.attention.wv": [
[
0.059997912496328354,
22
],
[
0.00023528531892225146,
0
]
],
"layers.18.attention.wo": [
[
0.03692711889743805,
22
],
[
0.00014481216203421354,
-1
]
],
"layers.18.feed_forward.w1": [
[
0.018235012888908386,
16
],
[
7.15096975909546e-05,
-1
]
],
"layers.18.feed_forward.w2": [
[
0.03604672849178314,
4
],
[
0.0001413596619386226,
-1
]
],
"layers.18.feed_forward.w3": [
[
0.018235012888908386,
16
],
[
7.15096975909546e-05,
-1
]
],
"layers.19.attention.wq": [
[
0.05455257371068001,
32
],
[
0.00021393051429186016,
0
]
],
"layers.19.attention.wk": [
[
0.05455257371068001,
32
],
[
0.00021393051429186016,
0
]
],
"layers.19.attention.wv": [
[
0.05455257371068001,
32
],
[
0.00021393051429186016,
0
]
],
"layers.19.attention.wo": [
[
0.024298356845974922,
-11
],
[
9.528754162602127e-05,
-1
]
],
"layers.19.feed_forward.w1": [
[
0.016636382788419724,
14
],
[
6.52406524750404e-05,
-1
]
],
"layers.19.feed_forward.w2": [
[
0.037912607192993164,
16
],
[
0.00014867674326524138,
0
]
],
"layers.19.feed_forward.w3": [
[
0.016636382788419724,
14
],
[
6.52406524750404e-05,
-1
]
],
"layers.20.attention.wq": [
[
0.05900881439447403,
26
],
[
0.00023140695702750236,
-1
]
],
"layers.20.attention.wk": [
[
0.05900881439447403,
26
],
[
0.00023140695702750236,
-1
]
],
"layers.20.attention.wv": [
[
0.05900881439447403,
26
],
[
0.00023140695702750236,
-1
]
],
"layers.20.attention.wo": [
[
0.029481958597898483,
-2
],
[
0.00011561506835278124,
0
]
],
"layers.20.feed_forward.w1": [
[
0.01973850466310978,
13
],
[
7.740584260318428e-05,
0
]
],
"layers.20.feed_forward.w2": [
[
0.05077813193202019,
15
],
[
0.00019912967400159687,
-1
]
],
"layers.20.feed_forward.w3": [
[
0.01973850466310978,
13
],
[
7.740584260318428e-05,
0
]
],
"layers.21.attention.wq": [
[
0.0625663548707962,
29
],
[
0.00024535812553949654,
0
]
],
"layers.21.attention.wk": [
[
0.0625663548707962,
29
],
[
0.00024535812553949654,
0
]
],
"layers.21.attention.wv": [
[
0.0625663548707962,
29
],
[
0.00024535812553949654,
0
]
],
"layers.21.attention.wo": [
[
0.02409578487277031,
-14
],
[
9.449264325667173e-05,
-1
]
],
"layers.21.feed_forward.w1": [
[
0.02278539538383484,
17
],
[
8.935417281463742e-05,
0
]
],
"layers.21.feed_forward.w2": [
[
0.07497410476207733,
1
],
[
0.0002940157719422132,
0
]
],
"layers.21.feed_forward.w3": [
[
0.02278539538383484,
17
],
[
8.935417281463742e-05,
0
]
],
"layers.22.attention.wq": [
[
0.05468488484621048,
23
],
[
0.0002144504978787154,
-1
]
],
"layers.22.attention.wk": [
[
0.05468488484621048,
23
],
[
0.0002144504978787154,
-1
]
],
"layers.22.attention.wv": [
[
0.05468488484621048,
23
],
[
0.0002144504978787154,
-1
]
],
"layers.22.attention.wo": [
[
0.025124160572886467,
6
],
[
9.852605580817908e-05,
0
]
],
"layers.22.feed_forward.w1": [
[
0.0270016361027956,
10
],
[
0.00010588859004201367,
-1
]
],
"layers.22.feed_forward.w2": [
[
0.10119497030973434,
6
],
[
0.00039684283547103405,
-1
]
],
"layers.22.feed_forward.w3": [
[
0.0270016361027956,
10
],
[
0.00010588859004201367,
-1
]
],
"layers.23.attention.wq": [
[
0.050478190183639526,
27
],
[
0.00019795302068814635,
0
]
],
"layers.23.attention.wk": [
[
0.050478190183639526,
27
],
[
0.00019795302068814635,
0
]
],
"layers.23.attention.wv": [
[
0.050478190183639526,
27
],
[
0.00019795302068814635,
0
]
],
"layers.23.attention.wo": [
[
0.0362025685608387,
-4
],
[
0.00014197066775523126,
-1
]
],
"layers.23.feed_forward.w1": [
[
0.0261356383562088,
11
],
[
0.00010249243496218696,
0
]
],
"layers.23.feed_forward.w2": [
[
0.16038192808628082,
-29
],
[
0.0006289482116699219,
-1
]
],
"layers.23.feed_forward.w3": [
[
0.0261356383562088,
11
],
[
0.00010249243496218696,
0
]
],
"layers.24.attention.wq": [
[
0.05497172102332115,
5
],
[
0.0002155762631446123,
0
]
],
"layers.24.attention.wk": [
[
0.05497172102332115,
5
],
[
0.0002155762631446123,
0
]
],
"layers.24.attention.wv": [
[
0.05497172102332115,
5
],
[
0.0002155762631446123,
0
]
],
"layers.24.attention.wo": [
[
0.03732874244451523,
-30
],
[
0.000146387072163634,
-1
]
],
"layers.24.feed_forward.w1": [
[
0.025813216343522072,
8
],
[
0.00010122814273927361,
0
]
],
"layers.24.feed_forward.w2": [
[
0.12522609531879425,
-27
],
[
0.000491082202643156,
-1
]
],
"layers.24.feed_forward.w3": [
[
0.025813216343522072,
8
],
[
0.00010122814273927361,
0
]
],
"layers.25.attention.wq": [
[
0.047167424112558365,
10
],
[
0.0001849701948231086,
-1
]
],
"layers.25.attention.wk": [
[
0.047167424112558365,
10
],
[
0.0001849701948231086,
-1
]
],
"layers.25.attention.wv": [
[
0.047167424112558365,
10
],
[
0.0001849701948231086,
-1
]
],
"layers.25.attention.wo": [
[
0.03641931712627411,
21
],
[
0.00014282084885053337,
0
]
],
"layers.25.feed_forward.w1": [
[
0.024308975785970688,
7
],
[
9.532903641229495e-05,
0
]
],
"layers.25.feed_forward.w2": [
[
0.22050899267196655,
-18
],
[
0.0008647405775263906,
0
]
],
"layers.25.feed_forward.w3": [
[
0.024308975785970688,
7
],
[
9.532903641229495e-05,
0
]
],
"layers.26.attention.wq": [
[
0.05102696269750595,
16
],
[
0.00020010532170999795,
-1
]
],
"layers.26.attention.wk": [
[
0.05102696269750595,
16
],
[
0.00020010532170999795,
-1
]
],
"layers.26.attention.wv": [
[
0.05102696269750595,
16
],
[
0.00020010532170999795,
-1
]
],
"layers.26.attention.wo": [
[
0.04784587025642395,
-11
],
[
0.0001876299938885495,
-1
]
],
"layers.26.feed_forward.w1": [
[
0.024701740592718124,
9
],
[
9.686937846709043e-05,
-1
]
],
"layers.26.feed_forward.w2": [
[
0.20375220477581024,
24
],
[
0.0007990262238308787,
-1
]
],
"layers.26.feed_forward.w3": [
[
0.024701740592718124,
9
],
[
9.686937846709043e-05,
-1
]
],
"layers.27.attention.wq": [
[
0.05648134648799896,
19
],
[
0.00022149378492031246,
-1
]
],
"layers.27.attention.wk": [
[
0.05648134648799896,
19
],
[
0.00022149378492031246,
-1
]
],
"layers.27.attention.wv": [
[
0.05648134648799896,
19
],
[
0.00022149378492031246,
-1
]
],
"layers.27.attention.wo": [
[
0.05714663490653038,
16
],
[
0.00022410399105865508,
0
]
],
"layers.27.feed_forward.w1": [
[
0.024300716817378998,
16
],
[
9.529681119602174e-05,
-1
]
],
"layers.27.feed_forward.w2": [
[
0.23974163830280304,
-23
],
[
0.0009401627467013896,
-1
]
],
"layers.27.feed_forward.w3": [
[
0.024300716817378998,
16
],
[
9.529681119602174e-05,
-1
]
],
"layers.28.attention.wq": [
[
0.05538808926939964,
18
],
[
0.00021720785298384726,
-1
]
],
"layers.28.attention.wk": [
[
0.05538808926939964,
18
],
[
0.00021720785298384726,
-1
]
],
"layers.28.attention.wv": [
[
0.05538808926939964,
18
],
[
0.00021720785298384726,
-1
]
],
"layers.28.attention.wo": [
[
0.04831133037805557,
1
],
[
0.00018945617193821818,
0
]
],
"layers.28.feed_forward.w1": [
[
0.02387886494398117,
10
],
[
9.364249854115769e-05,
-1
]
],
"layers.28.feed_forward.w2": [
[
0.21306206285953522,
16
],
[
0.0008355369791388512,
-1
]
],
"layers.28.feed_forward.w3": [
[
0.02387886494398117,
10
],
[
9.364249854115769e-05,
-1
]
],
"layers.29.attention.wq": [
[
0.05176341533660889,
23
],
[
0.00020299319294281304,
-1
]
],
"layers.29.attention.wk": [
[
0.05176341533660889,
23
],
[
0.00020299319294281304,
-1
]
],
"layers.29.attention.wv": [
[
0.05176341533660889,
23
],
[
0.00020299319294281304,
-1
]
],
"layers.29.attention.wo": [
[
0.06051347032189369,
-5
],
[
0.0002373075985815376,
0
]
],
"layers.29.feed_forward.w1": [
[
0.02441590465605259,
13
],
[
9.574845898896456e-05,
0
]
],
"layers.29.feed_forward.w2": [
[
0.2622620761394501,
-9
],
[
0.001028476282954216,
-1
]
],
"layers.29.feed_forward.w3": [
[
0.02441590465605259,
13
],
[
9.574845898896456e-05,
0
]
],
"layers.30.attention.wq": [
[
0.03940032795071602,
21
],
[
0.00015451051876880229,
-1
]
],
"layers.30.attention.wk": [
[
0.03940032795071602,
21
],
[
0.00015451051876880229,
-1
]
],
"layers.30.attention.wv": [
[
0.03940032795071602,
21
],
[
0.00015451051876880229,
-1
]
],
"layers.30.attention.wo": [
[
0.06193621829152107,
5
],
[
0.0002428869338473305,
-1
]
],
"layers.30.feed_forward.w1": [
[
0.029521800577640533,
-9
],
[
0.000115771617856808,
0
]
],
"layers.30.feed_forward.w2": [
[
0.2706244885921478,
-7
],
[
0.0010612712940201163,
-1
]
],
"layers.30.feed_forward.w3": [
[
0.029521800577640533,
-9
],
[
0.000115771617856808,
0
]
],
"layers.31.attention.wq": [
[
0.03465617075562477,
23
],
[
0.00013590618618763983,
0
]
],
"layers.31.attention.wk": [
[
0.03465617075562477,
23
],
[
0.00013590618618763983,
0
]
],
"layers.31.attention.wv": [
[
0.03465617075562477,
23
],
[
0.00013590618618763983,
0
]
],
"layers.31.attention.wo": [
[
0.04215332493185997,
18
],
[
0.00016530673019587994,
0
]
],
"layers.31.feed_forward.w1": [
[
0.04697251319885254,
-11
],
[
0.00018420587002765387,
0
]
],
"layers.31.feed_forward.w2": [
[
0.5093206763267517,
19
],
[
0.001997330691665411,
0
]
],
"layers.31.feed_forward.w3": [
[
0.04697251319885254,
-11
],
[
0.00018420587002765387,
0
]
],
"output": [
[
0.23516124486923218,
-15
],
[
0.0009221913642250001,
0
]
]
}
},
"host_data": "embed_tokens / vlm_meta.json / tokenizer exactly as in smolvlm-500m-instruct.py"
},
"files": {
"embed_tokens.i8.bin": {
"bytes": 47308800,
"sha256": "d3ea47247be0b0703ca1246335cb3bca5f68a4068e177475388e287d9eb5f385"
},
"embed_tokens.scale.f32.bin": {
"bytes": 197120,
"sha256": "adefdadaae81d572c6094b6826e850f263939d716b74da03484dc20c0769562a"
},
"vlm_meta.json": {
"bytes": 201,
"sha256": "b36fcf7ef7da8c2ace5271aa5da5ffaa5f10a779db2095cb69f5eadfc9972ae4"
},
"tokenizer/tokenizer.json": {
"sha256": "5ece781dc8d2b2f3e2f289ca0ae50b17cfc27dd27bfe7971bb8241e0b964331a"
},
"tokenizer/tokenizer_config.json": {
"sha256": "36c6fd44d07d10fd8180ee6b46dcccf69fb7c06753968ff0d7e17b8bfe17b777"
},
"tokenizer/special_tokens_map.json": {
"sha256": "aa0ff906077086dfa9734a7f97f68c825877a48f9468807be65504495cdeef09"
},
"smolvlm_vision_q8.pte": {
"bytes": 103839108,
"sha256": "a48d6919aa2067be9a8d615e46f1cac5c8e0ac94a6cea7af9e4798290f5a9747"
},
"smolvlm_decoder_q8.pte": {
"bytes": 366912132,
"sha256": "a54d81fbafd289c3b68891b150aa7ba9b069ffc5ecabe4114cc437fa726bc08a"
}
},
"graph": {
"smolvlm_vision_q8.pte": {
"forward": {
"inputs": [
{
"shape": [
1,
3,
512,
512
],
"dtype": "FLOAT"
}
],
"outputs": [
{
"shape": [
1,
64,
960
],
"dtype": "FLOAT"
}
],
"non_delegated_kernels": {},
"delegates": [
{
"id": "VulkanBackend",
"ops": {
"aten._softmax.default": 12,
"aten.add.Tensor": 171,
"aten.bmm.default": 24,
"aten.clamp.default": 73,
"aten.clone.default": 268,
"aten.convolution.default": 1,
"aten.gelu.default": 12,
"aten.mul.Tensor": 158,
"aten.native_layer_norm.default": 25,
"aten.permute_copy.default": 63,
"aten.round.default": 73,
"aten.squeeze_copy.dims": 48,
"aten.sub.Tensor": 146,
"aten.view_copy.default": 76,
"dim_order_ops._to_dim_order_copy.default": 146,
"et_vk.linear_q8ta_q8csw.default": 146,
"et_vk.prepack.default": 305,
"quantized_decomposed.quantize_per_tensor.default": 146
},
"op_arity": {
"aten._softmax.default": [
4
],
"aten.add.Tensor": [
4
],
"aten.bmm.default": [
3
],
"aten.clamp.default": [
4
],
"aten.clone.default": [
3
],
"aten.convolution.default": [
10
],
"aten.gelu.default": [
3
],
"aten.mul.Tensor": [
3
],
"aten.native_layer_norm.default": [
6
],
"aten.permute_copy.default": [
3
],
"aten.round.default": [
2
],
"aten.squeeze_copy.dims": [
3
],
"aten.sub.Tensor": [
4
],
"aten.view_copy.default": [
3
],
"dim_order_ops._to_dim_order_copy.default": [
8
],
"et_vk.linear_q8ta_q8csw.default": [
8
],
"et_vk.prepack.default": [
2
],
"quantized_decomposed.quantize_per_tensor.default": [
7
]
},
"inputs": 1,
"outputs": 1
}
]
}
},
"smolvlm_decoder_q8.pte": {
"forward": {
"inputs": [
{
"shape": [
1,
4,
960
],
"dtype": "FLOAT"
},
{
"shape": [
1
],
"dtype": "LONG"
}
],
"outputs": [
{
"shape": [
1,
49280
],
"dtype": "FLOAT"
}
],
"non_delegated_kernels": {},
"delegates": [
{
"id": "VulkanBackend",
"ops": {
"aten._to_copy.default": 482,
"aten.add.Tensor": 578,
"aten.clamp.default": 225,
"aten.clone.default": 450,
"aten.mul.Tensor": 610,
"aten.relu.default": 32,
"aten.round.default": 225,
"aten.select_copy.int": 1,
"aten.sigmoid.default": 32,
"aten.sub.Tensor": 546,
"aten.view_copy.default": 160,
"et_vk.apply_rotary_emb_hf.default": 32,
"et_vk.linear_q8ta_q8csw.default": 450,
"et_vk.prepack.default": 1030,
"et_vk.rms_norm.default": 65,
"et_vk.select_as_symint.default": 2,
"quantized_decomposed.quantize_per_tensor.default": 450,
"sdpa_with_kv_cache.default": 32
},
"op_arity": {
"aten._to_copy.default": [
8
],
"aten.add.Tensor": [
4
],
"aten.clamp.default": [
4
],
"aten.clone.default": [
3
],
"aten.mul.Tensor": [
3
],
"aten.relu.default": [
2
],
"aten.round.default": [
2
],
"aten.select_copy.int": [
4
],
"aten.sigmoid.default": [
2
],
"aten.sub.Tensor": [
4
],
"aten.view_copy.default": [
3
],
"et_vk.apply_rotary_emb_hf.default": [
6
],
"et_vk.linear_q8ta_q8csw.default": [
8
],
"et_vk.prepack.default": [
2
],
"et_vk.rms_norm.default": [
4
],
"et_vk.select_as_symint.default": [
4
],
"quantized_decomposed.quantize_per_tensor.default": [
7
],
"sdpa_with_kv_cache.default": [
12
]
},
"inputs": 2,
"outputs": 1
}
]
},
"get_max_context_len": {
"inputs": [],
"outputs": [
{
"value": 512
}
],
"non_delegated_kernels": {},
"delegates": []
},
"get_n_layers": {
"inputs": [],
"outputs": [
{
"value": 32
}
],
"non_delegated_kernels": {},
"delegates": []
},
"get_vocab_size": {
"inputs": [],
"outputs": [
{
"value": 49280
}
],
"non_delegated_kernels": {},
"delegates": []
},
"use_kv_cache": {
"inputs": [],
"outputs": [
{
"value": true
}
],
"non_delegated_kernels": {},
"delegates": []
},
"use_sdpa_with_kv_cache": {
"inputs": [],
"outputs": [
{
"value": true
}
],
"non_delegated_kernels": {},
"delegates": []
},
"enable_dynamic_shape": {
"inputs": [],
"outputs": [
{
"value": false
}
],
"non_delegated_kernels": {},
"delegates": []
},
"get_max_seq_len": {
"inputs": [],
"outputs": [
{
"value": 5
}
],
"non_delegated_kernels": {},
"delegates": []
}
}
},
"delegate_weight_check": {
"smolvlm_decoder_q8.pte": {
"linear_q8ta_q8csw_ops": 450,
"weight_int8_bit_identical": 450,
"weight_scales_bit_identical": 450,
"activation_qparams_match": 450,
"eager_q8_linears": 225
},
"smolvlm_vision_q8.pte": {
"linear_q8ta_q8csw_ops": 146,
"weight_int8_bit_identical": 146,
"weight_scales_bit_identical": 146,
"activation_qparams_match": 146,
"eager_q8_linears": 73
}
},
"command": "python recipes/smolvlm-500m-instruct-q8.py --out out/smolvlm-500m-instruct-q8"
}