From acaa2838cff66ada766f61851b2e34f67257856b Mon Sep 17 00:00:00 2001 From: wejoncy Date: Thu, 26 Oct 2023 14:22:07 +0800 Subject: [PATCH] Squashed commit of the following: commit 538e97cbda5e8c6c7c3a8796ce483da185f2e91c Author: Patrice Vignola Date: Wed Oct 25 19:56:16 2023 -0700 [DML EP] Add dynamic graph compilation (#17876) Historically, DML was only able to fuse partitions when all sizes are known in advance or when we were overriding them at session creation time. But in practice, it should be possible to compile partitions at compute time if the caller knows that the dimensions won't be changed for every inference (e.g. resizing a webcam window, or padding the input to powers of 2). This graph will be cached and reused until the sizes change. This is an opt-in option gated under the `enable_dynamic_graph_fusion` option, which means that it will only be enabled when the caller requests it since they have more context on how their model will be called between inferences. This PR also adds the option to disable metacommands from the python API, which is an option for the C API but was lacking for python. commit d30d4d372a33640aed78eb4bfe05db31e36f6e2a Author: Jambay Kinley Date: Wed Oct 25 15:34:58 2023 -0700 Add MatMul FP4 and NF4 Support (#18066) Add a contrib op MatMulBnb4 (FP4 and NF4) and related toolchain to support quantization on weight. This PR adds: - schema for contrib op MatMulBnb4 which can support FP4 (4-bit floating point) and NF4 (4-bit NormalFloat) quantization on weight. - a naive implementation for MatMulBnb4 on CPU and GPU, i.e., implemented like MatMul(A, Dequantize(B)). - a special implementation for GemV for MatMulBnb4 and related benchmark tool. - tool to quantize model to FP4 or NF4. commit d88d52eeadcdc2813e478dbb2d8dc6f5575258d6 Author: snadampal <87143774+snadampal@users.noreply.github.com> Date: Wed Oct 25 13:34:57 2023 -0500 [aarch64] Remove mmla kernel support from apple (#18082) The mmla kernels require additional ISA flags and are currently supported only on Linux more context is in https://github.com/microsoft/onnxruntime/pull/15270 cc: @skottmckay , @chenfucn , @snnn commit 706e13e0c95a730181bca62c348d3283a9194e11 Author: liqun Fu Date: Wed Oct 25 10:46:04 2023 -0700 implement affinegrid cpu kernel (#17777) commit 2c6b31c5aa05bdce26ccd1af58bb194f880166ed Author: pengwa Date: Wed Oct 25 15:11:02 2023 +0800 FP16 optimizer automatically detect DeepSpeed compatibility (#18084) Optimum/Transformers are using accelerate lib to prepare models, so our FP16 optimizer wrapper does not work for long time. Because the namespace is `accelerate.utils.deepspeed.DeepSpeedOptimizerWrapper`, which underlying is still calling into DeepSpeed stage1and2 optimizer. This PR includes following changes: 1. Add `accelerate.utils.deepspeed.DeepSpeedOptimizerWrapper` in the modifier registry, plus a check on its contained `optimizer` property MUST be DeepSpeed stage 1 and 2 optimizer. (let's cover Stage 3 optimizer later) 2. For DeepSpeed version > 0.9.1, we will store the source code in a version list. As long as the related function in DeepSpeed remains unchanged during its new release, we won't need manually upgrade the version check any more. If some day, the source code did not match, a warning will be raised to users, to add a new version of source code in the list. With the above change, we will have our FP16 Optimizer working again in Optimum. ![image](https://github.com/microsoft/onnxruntime/assets/10530022/d35b4aa9-b371-46f1-98ae-73114f91179b) commit ae8561979f494029c863dafb67bae05639ebff60 Author: Sumit Agarwal Date: Tue Oct 24 19:41:10 2023 -0700 Introduce new optimizer MatMul + BatchNormalization (#17915) Introduce new ORT L1 optimizer under RewriteRule category to fuse MatMul + BatchNormalization node. This optimizer look for a specific pattern observed in one of the impacting customer models and fuse the Matmul and Batchnormalization node into a Gemm node. For details on the pattern matching and fusion please refer to the comment section of `matmul_bn_fusion.cc`. To visualize, this optimizer will replace following subgraph to a Gemm node. 
                   MatMul                  GEMM
                     |                       |
                  Reshape ^     --->      Reshape ^
                     |                       |
                Transpose ^             Transpose ^
                     |
           BatchNormalization
    Note: ^ means there can be >=0 occurrence(s) of that node.
    Few example fusable pattern:
    * - MatMul -> Reshape -> Transpose -> BatchNormalization ---> GEMM ->
    Reshape -> Transpose
    * - MatMul -> Reshape -> BatchNormalization ---> GEMM -> Reshape
    * - MatMul -> Transpose -> BatchNormalization ---> GEMM -> Transpose
    * - MatMul -> Reshape -> Reshape -> BatchNormalization ---> GEMM ->
    Reshape -> Reshape
    * - MatMul -> Reshape -> Transpose -> Reshape -> BatchNormalization --->
    GEMM -> Reshape -> Transpose -> Reshape
    * - MatMul -> BatchNormalization ---> GEMM
Note: This optimizer may evolve in the future to be more generic in terms of the pattern matching. - Why is this change required? What problem does it solve? One of the user of ORT+DML ep needs this to better target the model to DML. But this transformation applies more broadly, so added L1 optimizer. commit 76e275baf44d5bd882fd298d3b86d824eb113435 Author: Jian Chen Date: Tue Oct 24 15:17:36 2023 -0700 Merge Cuda docker files into a single one (#18020) commit 6ec45f2ba590fabad99159a44fd6e48a5a9b03f0 Author: Changming Sun Date: Tue Oct 24 13:04:08 2023 -0700 Merge aiinfra-linux-ARM64-CPU-2019 and onnxruntime-linux-ARM64-CPU-2019 (#18069) Merge aiinfra-linux-ARM64-CPU-2019 and onnxruntime-linux-ARM64-CPU-2019 machines to a single one to ease management. commit efa0cc2562c28e6376717b46ebc83dd29b68d348 Author: liqun Fu Date: Tue Oct 24 10:58:54 2023 -0700 implement isinf20 and isnan20 (#17874) commit abb329179adae0029ef492c251984fcfd78224c4 Author: Changming Sun Date: Tue Oct 24 10:50:12 2023 -0700 Update win-wasm-ci.yml: increase the timeout value (#18023) commit e63ccd3cbb9e2479af94a69a0e2c9bb9b59a54e4 Author: Jian Chen Date: Tue Oct 24 10:47:23 2023 -0700 Install CUDA 12.2 on Windows (#18044) commit eb47008049a7aa0b617340bf2372723d0e873752 Author: Jiajia Qin Date: Tue Oct 24 13:56:56 2023 +0800 [js/webgpu] FP16 Cast, Resize (#18035) Cast/Resize with f16 are missing in vae-decoder-f16. With this change, vae-decoder-f16 becomes 315 ms from over than 1 seconds. commit 688524a9abca24d576297224cd48f92f283b0f11 Author: Tianlei Wu Date: Mon Oct 23 22:00:02 2023 -0700 [CUDA EP] Add warning logs when adding memcpy nodes (#18032) Memcpy nodes could have negative impact on performance, they also cause ORT unable to run CUDA graph. Here we add a warning log for CUDA EP when this happens. It could help trouble shooting. For example, when CUDA graph cannot run, we can see the logs to find out where the Memcpy nodes are inserted (Although it is also possible through saving optimized model, but that need more time and disk space). Note that the warning is per graph. When there are subgraphs, we might see multiple warnings if the issue happens in multiple graphs. Example logs: ``` 2023-10-19 20:58:10.678176531 [I:onnxruntime:, transformer_memcpy.cc:329 AddCopyNode] Add MemcpyFromHost after input_ids for CUDAExecutionProvider 2023-10-19 20:58:10.678198702 [I:onnxruntime:, transformer_memcpy.cc:329 AddCopyNode] Add MemcpyFromHost after /text_model/ArgMax_output_0 for CUDAExecutionProvider 2023-10-19 20:58:10.678211727 [I:onnxruntime:, transformer_memcpy.cc:329 AddCopyNode] Add MemcpyFromHost after /text_model/Gather_3_output_0 for CUDAExecutionProvider 2023-10-19 20:58:10.678257903 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 3 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message. ``` commit 555b2af7d67d56b3bd8b51dc375d7fd144c761d7 Author: Chi Lo <54722500+chilo-ms@users.noreply.github.com> Date: Tue Oct 24 02:41:15 2023 +0000 [TensorRT EP] Add unit test for user provided cuda stream (#17974) Add a unit test for testing user provided CUDA stream commit 4ffd022b0b1a62880d2498679f360878fdbbd796 Author: Chi Lo <54722500+chilo-ms@users.noreply.github.com> Date: Tue Oct 24 00:46:38 2023 +0000 [TensorRT EP] Refactor of TRT plugins support (#17946) Make sure "trt.plugins" custom op domain only being registered once. The bottom line is "trt.plugins" custom op domain needs to be registered before model load. `CreateTensorRTCustomOpDomainList()` is TRT EP's function to create "trt.plugins" custom op domain. Following are places where this function will be called. (This function only fetches all the TRT plugins from TRT plugin registry but not yet registered them to ORT custom op registry. The real registration happens in AddCustomOpDomains()) C/C++ APIs: - `OrtApis::SessionOptionsAppendExecutionProvider_TensorRT_XX`: This function will make session option object contain the "trt.plugins" custom op domain for ORT to register. So that later the session creation api can register the custom op domain accordingly and won't complain about invalid onnx node. - `InferenceSession::RegisterExecutionProvider`: In some cases, users might create the session object first and later call session_object.RegisterExecutionProvider(). This function will call p_exec_provider->GetCustomOpDomainList() which returns "trt.plugins" custom op domain. Otherwise, session_object.Load(model) will complain. Python APIs: - `RegisterTensorRTPluginsAsCustomOps`: Need to call this function so that session option object contains the "trt.plugins" custom op domain for ORT to register. Different language bindings have slightly different workflow of initializing the session. This might cause duplicate custom op domain in `session_option.custom_op_domains_` or `CreateTensorRTCustomOpDomainList()` being called more than once, but we put checks to make sure ep's custom op domain won't be registered twice. commit 2c50b75a26429ef3146d1c6c541f3a3112aa7c83 Author: Dmitri Smirnov Date: Mon Oct 23 17:42:20 2023 -0700 Functions Ahead Of Time inlininng (#17764) Inline functions in an EP aware fashion. The result of this PR is that models that are having been inlined by ONNX inliner and optimized and models that have been AOT inlined appear to be visually identical. For tests I used two models. The only difference is the resulting size because ONNX inliner removes local function definitions and AOT does not. Difference in sizes for `HF Mobile` model was 2.5 MB, and for `HF Bart` it was ~500K. It seems that the resuling model size affects the load time more than the actual optimizations. In general, the inlined models grow in size very fast and can easily exceed 2Gb limit. Q. Should we make AOT optional? `If` costant folding and the removal of local inlined models will be coming in other PRs. Some stats: ![image](https://github.com/microsoft/onnxruntime/assets/11303988/fcb4c815-2e06-4574-8d96-5a0a727d1ecf) commit f3cfe08c422be8671883fd3ae8617f05f22adb26 Author: satyajandhyala Date: Mon Oct 23 16:02:50 2023 -0700 [JS/Web] Enabled 1d spacial input to GlobalAveragePool (#17973) Enable one-dim special input to GlobalAveragePoll input Currently only 2D input is supported. commit 780ee186d72b74a77c4a2752d7a84c3807206ee6 Author: snadampal <87143774+snadampal@users.noreply.github.com> Date: Mon Oct 23 16:49:04 2023 -0500 [aarch64] Implement QGEMM kernels with UMMLA/SMMLA instructions (#17160) This PR adds UMMLA and SMMLA based QGEMM kernels for aarch64. This covers (i) symmetric quantization (zero point is Zero) (ii) asymmetric quantization (zero point is non zero) (iii) per channel as well as per tensor quantization (iv) Signed weights (U8S8 Gemm) (v) Unsigned weights (U8U8 Gemm) and (vi) Signed activations and weights (S8S8 Gemm) scenarios I've enabled the ummla/smmla kernels based on cpuinfo check for `I8MM` support MMLA QGEMM kernels are enabled for all the devices that support I8MM instructions. This is to improve INT8 quantized MatMul performance on aarch64 platform. I have run the below benchmarking script (bert , roberta and gpt2 model inference) on AWS Graviton3 based c7g.4xl instance and observed up to 1.33x performance improvement compared to the optimized UDOT qgemm kernel performance. ``` cd onnxruntime/python/tools/transformers python3 benchmark.py ``` I have also run the unit tests, and made sure all are passing ``` ./build.sh --config RelWithDebInfo --build_shared_lib --parallel --compile_no_warning_as_error --skip_submodule_sync ``` commit 2a17d5cf32900fa0100959eace6e303c82f86bdc Author: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com> Date: Mon Oct 23 13:00:56 2023 -0700 LLaMA Model Optimization (#18021) This PR contains fusion-level and kernel-level optimizations for [Meta's LLaMA-2](https://blogs.microsoft.com/blog/2023/07/18/microsoft-and-meta-expand-their-ai-partnership-with-llama-2-on-azure-and-windows/). Some of the added optimizations include: - SimplifiedLayerNorm changes - Fusions for multiple variants - SkipSimplifiedLayerNorm changes - Kernel support for CPU - Rotary embeddings (previously did not exist) - Fusions for multiple variants - CPU and CUDA kernels - Supports interleaving and non-interleaving in the same kernels - Optimized cache that requires half of its originally exported sizes - Reduced from `(max_sequence_length, head_size)` to `(max_sequence_length, head_size / 2)` - Multi-head attention - Support for 2D and 3D attention masks - Group query attention (for FP16 CUDA and INT4 CUDA) - Integration with flash attention v2 and past-present buffer sharing - Removes need for `attention_mask` input as it is supported in the kernel - 4 bit quantization - `block_size` parameter is available for customizing - Support the new changes for [Microsoft version](https://github.com/microsoft/Llama-2-Onnx) - Support combinations of the below variants (ex: export ORT version and run with Optimum) Supported variants of LLaMA-2 include: - [ORT version](https://github.com/microsoft/onnxruntime/tree/main/onnxruntime/python/tools/transformers/models/llama) - Produces one ONNX file that is already optimized (and quantized if requested) - Integrates with Optimum - [Another Microsoft version](https://github.com/microsoft/Llama-2-Onnx) - Already exported and available off-the-shelf - Faster versions of those models will be uploaded there soon - [Hugging Face version](https://huggingface.co/meta-llama) - Models that end with `-hf` - Some older and current versions of [`transformers`](https://github.com/huggingface/transformers) and [`optimum`](https://github.com/huggingface/optimum) that export the model to ONNX differently - Note that while some older versions are supported, it is recommended to use the latest package versions. To use the optimizations, please see `README.md` for details. Please note the various `requirements.txt` files for the package versions recommended in order to use these changes. To run the ORT transformer optimizer separately, run the script as follows: ``` $ cd onnxruntime/onnxruntime/python/tools/transformers/ $ python3 optimizer.py --input .onnx --output .onnx --model_type gpt2 --num_heads --hidden_size