Enabled VLMs via CLI #287
Open
Enabled VLMs via CLI #287
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ochougul
requested changes
Feb 27, 2025
quic-amitraj
requested changes
Feb 27, 2025
quic-amitraj
requested changes
Mar 3, 2025
asmigosw
force-pushed
the
image_text_support
branch
from
9567658 to
ad06845
Compare
asmigosw
force-pushed
the
image_text_support
branch
from
bc60d47 to
76e863a
Compare
asmigosw
force-pushed
the
image_text_support
branch
from
76e863a to
8d99a93
Compare
Removing onnx_defer_loading flag which was originally removed in _[Removed onnx_defer_loading from Immutable Convertor Args. PR: 230]_ but got added back later in _[Mllama(single + dual) + InternVL(single) + Llava (single) PR: 267]_ maybe becausing of rebasing. Signed-off-by: Shubham Agrawal <[email protected]> Signed-off-by: Asmita Goswami <[email protected]>
This will create a config JSON file, which contains all the details
about compilation and SDK versions.
Currently, this code is added in the code block of
QEFFAutoModelForCausalLM.compile.
The config would look like below:
```
{
"huggingface_config": {
"vocab_size": 50257,
"n_positions": 1024,
"n_embd": 768,
"n_layer": 12,
"n_head": 12,
"n_inner": null,
"activation_function": "gelu_new",
"resid_pdrop": 0.1,
"embd_pdrop": 0.1,
"attn_pdrop": 0.1,
"layer_norm_epsilon": 1e-05,
"initializer_range": 0.02,
"summary_type": "cls_index",
"summary_use_proj": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"scale_attn_weights": true,
"use_cache": true,
"scale_attn_by_inverse_layer_idx": false,
"reorder_and_upcast_attn": false,
"bos_token_id": 50256,
"eos_token_id": 50256,
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": null,
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"GPT2LMHeadModel"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"pad_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"problem_type": null,
"_name_or_path": "gpt2",
"_commit_hash": "607a30d783dfa663caf39e06633721c8d4cfcd7e",
"_attn_implementation_internal": "eager",
"transformers_version": null,
"model_type": "gpt2",
"n_ctx": 1024
},
"qpc_config": {
"QEff_config": {
"pytorch_transforms": [
"AwqToMatmulNbitsTransform",
"GPTQToMatmulNbitsTransform",
"CustomOpsTransform",
"KVCacheTransform"
],
"onnx_transforms": [
"FP16ClipTransform",
"SplitTensorsTransform"
],
"onnx_path": "/root/.cache/qeff_models/GPT2LMHeadModel-36f0eca92731bb47/GPT2LMHeadModel.onnx"
},
"aic_compiler_config": {
"apps_sdk_version": "1.20.0",
"compile_dir": "/root/.cache/qeff_models/GPT2LMHeadModel-36f0eca92731bb47",
"specializtions_file_path": "/root/.cache/qeff_models/GPT2LMHeadModel-36f0eca92731bb47/specializations.json",
"prefill_seq_len": 32,
"ctx_len": 128,
"batch_size": 1,
"full_batch_size": null,
"num_devices": 1,
"num_cores": 16,
"mxfp6_matmul": false,
"mxint8_kv_cache": false,
"num_speculative_tokens": null
},
"qnn_config": {
"enable_qnn": true,
"qnn_config_path": "QEfficient/compile/qnn_config.json",
"product": "QAIRT",
"os": {
"Ubuntu": 22.04,
"Windows": 11
},
"sdk_flavor": [
"aic"
],
"version": "2.31.0",
"build_id": "250109072054_3882",
"qnn_backend_api_version": "2.18.0",
"tensorflow": "2.10.1",
"tflite": "2.3.0",
"torch": "1.13.1",
"onnx": "1.16.1",
"onnxruntime": "1.17.1",
"onnxsimplifier": "0.4.36",
"android-ndk": "r26c",
"platform": "AIC.1.20.0.14"
}
}
}
```
Note: The code structure may change.
---------
Signed-off-by: Abukhoyer Shaik <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
… validation page (quic#303) Signed-off-by: Abukhoyer Shaik <[email protected]> Signed-off-by: Asmita Goswami <[email protected]>
This is just small fixes done for printing the `QEFFAutoModelForCausalLM`'s instance by changing the `__repr__(self)` method. Signed-off-by: Abukhoyer Shaik <[email protected]> Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
Signed-off-by: Asmita Goswami <[email protected]>
asmigosw
force-pushed
the
image_text_support
branch
from
3165896 to
1608804
Compare
Signed-off-by: Asmita Goswami <[email protected]>
asmigosw
force-pushed
the
image_text_support
branch
from
b08404d to
ca55d42
Compare
Signed-off-by: Asmita Goswami <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added support for enabling VLMs via CLI.
Sample command:
python -m QEfficient.cloud.infer --model_name meta-llama/Llama-3.2-11B-Vision-Instruct --batch_size 1 --prompt_len 32 --ctx_len 512 --num_cores 16 --device_group [0] --prompt "Descrive the image?" --mos 1 --allocator_dealloc_delay 1 --image_url https://i.etsystatic.com/8155076/r/il/0825c2/1594869823/il_fullxfull.1594869823_5x0w.jpg