From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by smtp.lore.kernel.org (Postfix) with ESMTP id BBEF3C9832F for ; Sun, 18 Jan 2026 19:17:02 +0000 (UTC) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 5327442D9D; Sun, 18 Jan 2026 20:14:27 +0100 (CET) Received: from mail-ed1-f44.google.com (mail-ed1-f44.google.com [209.85.208.44]) by mails.dpdk.org (Postfix) with ESMTP id EF82342D26 for ; Sun, 18 Jan 2026 20:14:24 +0100 (CET) Received: by mail-ed1-f44.google.com with SMTP id 4fb4d7f45d1cf-64b9cb94ff5so5296265a12.2 for ; Sun, 18 Jan 2026 11:14:24 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1768763664; x=1769368464; darn=dpdk.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=fPIb96oVwaZt3kLEdSG6WT1jK0ZdmENEbD6xiJzZ8gE=; b=xAnNVv9TCY+mTEVWqkT7KeuWQxyr9xGvX5CDdaojBSftndQOKIpKmgcQ8Mi4FmSQbh 1vfB/YZLcG/D1VMNYZBw6OB9hFiqK4OTv7DaH+1ry0RXLrlLDIfyvDsv3SKygadvHkd3 YkotchY4s7b+nN6zpJUdZJKq1BxtVT5KCg6xQe5tlObtpvN6g19oq+ZQyjhiAMo95awD K4cTCkoK+D6AtFJMWVDIRgrRyEJRySS+u2W9rFrr84YGHNSfFh+nfblwGisoinzx61t4 zn4BE+lcjd+IyGER1v8ao6L+wmNPAgR/cnWKoCrKhwi9c30XU3ncAPuz6j87eps97KIq Rjlw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768763664; x=1769368464; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=fPIb96oVwaZt3kLEdSG6WT1jK0ZdmENEbD6xiJzZ8gE=; b=SmQHlIbnf4ZxkU4HHVcxpHSP3FHrdZO3lwtjH3pzOQR+pWshEBQOZOwlB6bLwl8tEu RD8+EZjlwvb1CKdlIHr3lvCrAFrOV9xBlGdoFGAsPUqVDAjfk9s6U4n6bv0xt+vUnBFn OuPEeru7Zv/9jHKAD88D69D2wvMwSzztDHBddWlkAcM+RtRZ8X1hWmZc1I2UUApJR7Ym WYzqc4tg2TSmrW5+YbZE9Qr+7sP6X5OOj1XfLOlEAvQf8osQM4CBrNHoXKUCmVEiSNmZ F6LfnRl7PKHyMAQ+z/TbQwI10umBXXgCcUtkb0EKIkQ+vGGDPtrAZ7G42PUcTtThgE9R PtMg== X-Gm-Message-State: AOJu0YymRga4azp3l2uIy45Cy3SLwgj6uq4pKgQvnFuBHo0yf4u7AF3P d4k1O9uXe5GAeUtzCObx7yrA+uBLsvfNsYHcSuyw7gY4NT8njwVFhJCDu6V1O1ex34fl8mqzdDb obi22 X-Gm-Gg: AY/fxX4KVnuQLBxeaqjR/5o65oNg8zoa78LFvwftjwt521Xdop68YK++WluEDsP1biZ V7x6fj5tWVkftXmTLdG9hUIXU/xXmB8kByYnNIzHBa2SEN+qcKJqiz3i5Payy8wQDCWhstGOC8B AInwVIvTYkfKWiy2uMNgDbbCYjvbl/jAd2RNnM+rAnq1mmNyZcmRm4r7dQoMtE2cR+yeiPYXELK eshFsCJFnZExwsswrgcXdlGPb+ILOxKqXh09K/havo7p12A2z3vXnpAmbQbQ6Q9Z+fYvcaK/G0A HKWISPYvcnByc+pZqjyl+oKdf5ACIGawGOSniuQUzVMmNj2e9RF0KU7cmRLWRsLeAi70rL9Do6r cHNl2CC0S4Zy+F4cDtsPJK3LH5/UUjmUf5AdNITj0glLt4v9SODqIg0kVbUNT2o2GYOSrk7p6TI ugfmgoU9CHNcBTo5iGVITao6+YovafzBLRHPKEDfp8fasSMnx/eA== X-Received: by 2002:a17:907:743:b0:b83:8fc:c64b with SMTP id a640c23a62f3a-b879300a356mr753923466b.38.1768763664440; Sun, 18 Jan 2026 11:14:24 -0800 (PST) Received: from phoenix.lan (204-195-96-226.wavecable.com. [204.195.96.226]) by smtp.gmail.com with ESMTPSA id a640c23a62f3a-b87959c9f8dsm886287166b.36.2026.01.18.11.14.23 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 18 Jan 2026 11:14:24 -0800 (PST) From: Stephen Hemminger To: dev@dpdk.org Cc: Stephen Hemminger Subject: [PATCH v5 36/54] doc: correct grammar in mldev library guide Date: Sun, 18 Jan 2026 11:10:39 -0800 Message-ID: <20260118191323.241013-37-stephen@networkplumber.org> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20260118191323.241013-1-stephen@networkplumber.org> References: <20240513155911.31872-1-nandinipersad361@gmail.com> <20260118191323.241013-1-stephen@networkplumber.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Correct various grammar and style issues in the ML device library documentation: - fix subject-verb agreement for "API which supports" - use compound word "Workflow" instead of "Work flow" - fix parallel construction for model load and start - use plural "feature sets" - rewrite grammatically broken sentence about rte_ml_dev_info_get - add missing article before "number of queue pairs" - use consistent terminology "operations" not "packets" - fix malformed sentence about dequeue API format - add missing word "with" in quantize section Signed-off-by: Stephen Hemminger --- doc/guides/prog_guide/mldev.rst | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/doc/guides/prog_guide/mldev.rst b/doc/guides/prog_guide/mldev.rst index 61661b998b..094a67cbdb 100644 --- a/doc/guides/prog_guide/mldev.rst +++ b/doc/guides/prog_guide/mldev.rst @@ -6,7 +6,7 @@ Machine Learning (ML) Device Library The Machine Learning (ML) Device library provides a Machine Learning device framework for the management and provisioning of hardware and software ML poll mode drivers, -defining an API which support a number of ML operations +defining an API which supports a number of ML operations including device handling and inference processing. The ML model creation and training is outside of the scope of this library. @@ -16,7 +16,7 @@ The ML framework is built on the following model: .. figure:: img/mldev_flow.* - Work flow of inference on MLDEV + Workflow of inference on MLDEV ML Device A hardware or software-based implementation of ML device API @@ -28,7 +28,7 @@ ML Model required to make predictions on live data. Once the model is created and trained outside of the DPDK scope, the model can be loaded via ``rte_ml_model_load()`` - and then start it using ``rte_ml_model_start()`` API function. + and then started using ``rte_ml_model_start()`` API function. The ``rte_ml_model_params_update()`` can be used to update the model parameters such as weights and bias without unloading the model using ``rte_ml_model_unload()``. @@ -79,9 +79,9 @@ Each device, whether virtual or physical is uniquely designated by two identifie Device Features and Capabilities ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -ML devices may support different feature set. -In order to get the supported PMD feature ``rte_ml_dev_info_get()`` API -which return the info of the device and its supported features. +ML devices may support different feature sets. +To get the supported PMD features, use the ``rte_ml_dev_info_get()`` API, +which returns the info of the device and its supported features. Device Configuration @@ -106,7 +106,7 @@ maximum size of model and so on. Configuration of Queue Pairs ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Each ML device can be configured with number of queue pairs. +Each ML device can be configured with a number of queue pairs. Each queue pair is configured using ``rte_ml_dev_queue_pair_setup()`` @@ -162,9 +162,9 @@ to specify the device queue pair to schedule the processing on. The ``nb_ops`` parameter is the number of operations to process which are supplied in the ``ops`` array of ``rte_ml_op`` structures. The enqueue function returns the number of operations it enqueued for processing, -a return value equal to ``nb_ops`` means that all packets have been enqueued. +a return value equal to ``nb_ops`` means that all operations have been enqueued. -The dequeue API uses the same format as the enqueue API of processed +The dequeue API uses the same format as the enqueue API, but the ``nb_ops`` and ``ops`` parameters are now used to specify the max processed operations the user wishes to retrieve and the location in which to store them. @@ -193,7 +193,7 @@ from a higher precision type to a lower precision type and vice-versa. ML library provides the functions ``rte_ml_io_quantize()`` and ``rte_ml_io_dequantize()`` to enable data type conversions. User needs to provide the address of the quantized and dequantized data buffers -to the functions, along the number of the batches in the buffers. +to the functions, along with the number of batches in the buffers. For quantization, the dequantized data is assumed to be of the type ``dtype`` provided by the ``rte_ml_model_info::input`` -- 2.51.0