From 2358ca527bd0d2f8a99ced33586cc0d72ed51092 Mon Sep 17 00:00:00 2001 From: Harry Mellor <19981378+hmellor@users.noreply.github.com> Date: Tue, 18 Feb 2025 10:52:39 +0000 Subject: [PATCH] [Doc]: Improve feature tables (#13224) Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> --- docs/source/_static/custom.css | 8 + docs/source/conf.py | 9 +- docs/source/features/compatibility_matrix.md | 153 +++++++++--------- .../quantization/supported_hardware.md | 94 +++++------ docs/source/models/pooling_models.md | 8 +- 5 files changed, 143 insertions(+), 129 deletions(-) create mode 100644 docs/source/_static/custom.css diff --git a/docs/source/_static/custom.css b/docs/source/_static/custom.css new file mode 100644 index 0000000000000..79bd2082b49e8 --- /dev/null +++ b/docs/source/_static/custom.css @@ -0,0 +1,8 @@ +.vertical-table-header th.head:not(.stub) { + writing-mode: sideways-lr; + white-space: nowrap; + max-width: 0; + p { + margin: 0; + } +} diff --git a/docs/source/conf.py b/docs/source/conf.py index f4e8c8b949102..84c9a27be3bf0 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -78,8 +78,12 @@ html_theme_options = { 'use_repository_button': True, 'use_edit_page_button': True, } +# Add any paths that contain custom static files (such as style sheets) here, +# relative to this directory. They are copied after the builtin static files, +# so a file named "default.css" will overwrite the builtin "default.css". html_static_path = ["_static"] html_js_files = ["custom.js"] +html_css_files = ["custom.css"] myst_url_schemes = { 'http': None, @@ -121,11 +125,6 @@ if READTHEDOCS_VERSION_TYPE == "tag": if os.path.exists(header_file): os.remove(header_file) -# Add any paths that contain custom static files (such as style sheets) here, -# relative to this directory. They are copied after the builtin static files, -# so a file named "default.css" will overwrite the builtin "default.css". -# html_static_path = ['_static'] - # Generate additional rst documentation here. def setup(app): diff --git a/docs/source/features/compatibility_matrix.md b/docs/source/features/compatibility_matrix.md index ee5db70c7d5c8..6056ca0d366b5 100644 --- a/docs/source/features/compatibility_matrix.md +++ b/docs/source/features/compatibility_matrix.md @@ -4,8 +4,14 @@ The tables below show mutually exclusive features and the support on some hardware. +The symbols used have the following meanings: + +- ✅ = Full compatibility +- 🟠 = Partial compatibility +- ❌ = No compatibility + :::{note} -Check the '✗' with links to see tracking issue for unsupported feature/hardware combination. +Check the ❌ or 🟠 with links to see tracking issue for unsupported feature/hardware combination. ::: ## Feature x Feature @@ -29,6 +35,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar :header-rows: 1 :stub-columns: 1 :widths: auto +:class: vertical-table-header - * Feature * [CP](#chunked-prefill) @@ -48,7 +55,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * beam-search * guided dec - * [CP](#chunked-prefill) - * + * ✅ * * * @@ -66,7 +73,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * - * [APC](#automatic-prefix-caching) * ✅ - * + * ✅ * * * @@ -82,9 +89,9 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * * - * [LoRA](#lora-adapter) - * [✗](gh-pr:9057) * ✅ - * + * ✅ + * ✅ * * * @@ -102,7 +109,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * + * ✅ * * * @@ -118,9 +125,9 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar - * [SD](#spec_decode) * ✅ * ✅ - * ✗ + * ❌ + * ✅ * ✅ - * * * * @@ -138,7 +145,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * + * ✅ * * * @@ -150,13 +157,13 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * * - * pooling - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ - * + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ + * ✅ * * * @@ -167,14 +174,14 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * * - * enc-dec - * ✗ - * [✗](gh-issue:7366) - * ✗ - * ✗ - * [✗](gh-issue:7366) + * ❌ + * [❌](gh-issue:7366) + * ❌ + * ❌ + * [❌](gh-issue:7366) + * ✅ * ✅ * ✅ - * * * * @@ -190,9 +197,9 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ✗ + * ❌ + * ✅ * ✅ - * * * * @@ -205,12 +212,12 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * [✗](gh-pr:8199) - * ✅ - * ✗ * ✅ * ✅ - * + * ❌ + * ✅ + * ✅ + * ✅ * * * @@ -222,49 +229,49 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ✗ + * ❌ + * ✅ + * ❌ + * ❌ * ✅ - * ✗ - * ✗ * ✅ * ✅ - * * * * * * - * multi-step - * ✗ + * ❌ * ✅ - * ✗ + * ❌ + * ✅ + * ❌ + * ✅ + * ❌ + * ❌ * ✅ - * ✗ * ✅ - * ✗ - * ✗ * ✅ - * [✗](gh-issue:8198) * ✅ - * * * * * - * mm * ✅ - * [✗](gh-pr:8348) - * [✗](gh-pr:7199) - * ? - * ? + * [🟠](gh-pr:8348) + * [🟠](gh-pr:4194) + * ❔ + * ❔ * ✅ * ✅ * ✅ * ✅ * ✅ * ✅ - * ? - * + * ❔ + * ✅ * * * @@ -273,16 +280,16 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * [✗](gh-issue:6137) + * [❌](gh-issue:6137) * ✅ - * ✗ + * ❌ * ✅ * ✅ * ✅ - * ? - * [✗](gh-issue:7968) + * ❔ + * [❌](gh-issue:7968) + * ✅ * ✅ - * * * - * beam-search @@ -290,35 +297,35 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * [✗](gh-issue:6137) + * [❌](gh-issue:6137) * ✅ - * ✗ + * ❌ * ✅ * ✅ * ✅ - * ? - * [✗](gh-issue:7968) - * ? + * ❔ + * [❌](gh-issue:7968) + * ❔ + * ✅ * ✅ - * * - * guided dec * ✅ * ✅ - * ? - * ? - * [✗](gh-issue:11484) + * ❔ + * ❔ + * [❌](gh-issue:11484) * ✅ - * ✗ - * ? + * ❌ + * ❔ * ✅ * ✅ * ✅ - * [✗](gh-issue:9893) - * ? + * [❌](gh-issue:9893) + * ❔ + * ✅ * ✅ * ✅ - * ::: (feature-x-hardware)= @@ -339,7 +346,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * CPU * AMD - * [CP](#chunked-prefill) - * [✗](gh-issue:2729) + * [❌](gh-issue:2729) * ✅ * ✅ * ✅ @@ -347,7 +354,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ - * [APC](#automatic-prefix-caching) - * [✗](gh-issue:3687) + * [❌](gh-issue:3687) * ✅ * ✅ * ✅ @@ -368,7 +375,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * [✗](gh-issue:8475) + * [❌](gh-issue:8475) * ✅ - * [SD](#spec_decode) * ✅ @@ -384,7 +391,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ✗ + * ❌ * ✅ - * pooling * ✅ @@ -393,7 +400,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ? + * ❔ - * enc-dec * ✅ * ✅ @@ -401,7 +408,7 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ✗ + * ❌ - * mm * ✅ * ✅ @@ -432,15 +439,15 @@ Check the '✗' with links to see tracking issue for unsupported feature/hardwar * ✅ * ✅ * ✅ - * ✗ - * ✗ + * ❌ + * ❌ - * multi-step * ✅ * ✅ * ✅ * ✅ * ✅ - * [✗](gh-issue:8477) + * [❌](gh-issue:8477) * ✅ - * best-of * ✅ diff --git a/docs/source/features/quantization/supported_hardware.md b/docs/source/features/quantization/supported_hardware.md index 555ed4ce4c8db..a5bd8caf77cd0 100644 --- a/docs/source/features/quantization/supported_hardware.md +++ b/docs/source/features/quantization/supported_hardware.md @@ -20,93 +20,93 @@ The table below shows the compatibility of various quantization implementations * AWS Inferentia * Google TPU - * AWQ - * ✗ + * ❌ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ + * ❌ * ✅︎ * ✅︎ - * ✗ - * ✗ + * ❌ + * ❌ - * GPTQ * ✅︎ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ + * ❌ * ✅︎ * ✅︎ - * ✗ - * ✗ + * ❌ + * ❌ - * Marlin (GPTQ/AWQ/FP8) - * ✗ - * ✗ + * ❌ + * ❌ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ - * INT8 (W8A8) - * ✗ + * ❌ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ + * ❌ + * ❌ * ✅︎ - * ✗ - * ✗ + * ❌ + * ❌ - * FP8 (W8A8) - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ - * AQLM * ✅︎ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ - * bitsandbytes * ✅︎ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ - * DeepSpeedFP * ✅︎ * ✅︎ * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ + * ❌ - * GGUF * ✅︎ * ✅︎ @@ -114,16 +114,16 @@ The table below shows the compatibility of various quantization implementations * ✅︎ * ✅︎ * ✅︎ - * ✗ - * ✗ - * ✗ - * ✗ + * ❌ + * ❌ + * ❌ + * ❌ ::: - Volta refers to SM 7.0, Turing to SM 7.5, Ampere to SM 8.0/8.6, Ada to SM 8.9, and Hopper to SM 9.0. -- "✅︎" indicates that the quantization method is supported on the specified hardware. -- "✗" indicates that the quantization method is not supported on the specified hardware. +- ✅︎ indicates that the quantization method is supported on the specified hardware. +- ❌ indicates that the quantization method is not supported on the specified hardware. :::{note} This compatibility chart is subject to change as vLLM continues to evolve and expand its support for different hardware platforms and quantization methods. diff --git a/docs/source/models/pooling_models.md b/docs/source/models/pooling_models.md index 9704ccee745c4..764b67241999e 100644 --- a/docs/source/models/pooling_models.md +++ b/docs/source/models/pooling_models.md @@ -28,10 +28,10 @@ The selected option sets the default pooler used to extract the final hidden sta - * Embedding (`embed`) * `LAST` * ✅︎ - * ✗ + * ❌ - * Classification (`classify`) * `LAST` - * ✗ + * ❌ * ✅︎ - * Sentence Pair Scoring (`score`) * \* @@ -39,8 +39,8 @@ The selected option sets the default pooler used to extract the final hidden sta * \* - * Reward Modeling (`reward`) * `ALL` - * ✗ - * ✗ + * ❌ + * ❌ ::: \*The default pooler is always defined by the model.