From 46ec52a46280da578dff3afe641a14bf9a2e8d1f Mon Sep 17 00:00:00 2001 From: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> Date: Thu, 15 Jan 2026 09:02:13 -0800 Subject: [PATCH 1/3] doc: Adding supported GPUs to doc Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> --- docs/source/overview.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/source/overview.md b/docs/source/overview.md index e7aeed43a237..2619b5b77537 100644 --- a/docs/source/overview.md +++ b/docs/source/overview.md @@ -54,8 +54,9 @@ TensorRT LLM strives to support the most popular models on **Day 0**. ### 🔧 **Latest GPU Architecture Support** TensorRT LLM supports the full spectrum of NVIDIA GPU architectures: -- **NVIDIA Blackwell**: B200, GB200, B300, GB300, and RTX Pro 6000 SE with FP4 optimization -- **NVIDIA Ada Lovelace**: L40/L40S, RTX 40 series with FP8 acceleration +- **NVIDIA Blackwell**: B200, GB200, B300, GB300, DGX Spark, RTX 6000D and RTX Pro 6000 SE with FP4 optimization +- **NVIDIA Hopper**: H100, H200, GH200 +- **NVIDIA Ada Lovelace**: L20, L40/L40S, RTX 40 series with FP8 acceleration - **NVIDIA Ampere**: A100, RTX 30 series for production workloads ## What Can You Do With TensorRT LLM? From 3678ea2a64b919742d1f319f18ae45c6db45311a Mon Sep 17 00:00:00 2001 From: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> Date: Tue, 20 Jan 2026 05:22:28 -0800 Subject: [PATCH 2/3] Removing RTX cards from supported GPUs Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> --- docs/source/overview.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/source/overview.md b/docs/source/overview.md index 2619b5b77537..9a96307b86c4 100644 --- a/docs/source/overview.md +++ b/docs/source/overview.md @@ -54,10 +54,10 @@ TensorRT LLM strives to support the most popular models on **Day 0**. ### 🔧 **Latest GPU Architecture Support** TensorRT LLM supports the full spectrum of NVIDIA GPU architectures: -- **NVIDIA Blackwell**: B200, GB200, B300, GB300, DGX Spark, RTX 6000D and RTX Pro 6000 SE with FP4 optimization +- **NVIDIA Blackwell**: B200, GB200, B300, GB300, DGX Spark - **NVIDIA Hopper**: H100, H200, GH200 -- **NVIDIA Ada Lovelace**: L20, L40/L40S, RTX 40 series with FP8 acceleration -- **NVIDIA Ampere**: A100, RTX 30 series for production workloads +- **NVIDIA Ada Lovelace**: L20, L40/L40S +- **NVIDIA Ampere**: A100 ## What Can You Do With TensorRT LLM? From 0939de4c31ca0cbcd1e674e83f44c8aa44943980 Mon Sep 17 00:00:00 2001 From: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> Date: Tue, 20 Jan 2026 06:36:15 -0800 Subject: [PATCH 3/3] Moving supported hardware to standalone page Signed-off-by: Patrice Castonguay <55748270+pcastonguay@users.noreply.github.com> --- docs/source/index.rst | 1 + docs/source/overview.md | 8 -------- docs/source/supported-hardware.md | 7 +++++++ 3 files changed, 8 insertions(+), 8 deletions(-) create mode 100644 docs/source/supported-hardware.md diff --git a/docs/source/index.rst b/docs/source/index.rst index 49c5e1546cc1..52c56be85e92 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -14,6 +14,7 @@ Welcome to TensorRT LLM's Documentation! overview.md quick-start-guide.md installation/index.rst + supported-hardware.md .. toctree:: diff --git a/docs/source/overview.md b/docs/source/overview.md index 9a96307b86c4..0eee6b6f9fd7 100644 --- a/docs/source/overview.md +++ b/docs/source/overview.md @@ -51,14 +51,6 @@ TensorRT LLM strives to support the most popular models on **Day 0**. - **[Guided Decoding](./features/guided-decoding.md)**: Advanced sampling with stop words, bad words, and custom constraints - **[Disaggregated Serving (Beta)](./features/disagg-serving.md)**: Separate context and generation phases across different GPUs for optimal resource utilization -### 🔧 **Latest GPU Architecture Support** - -TensorRT LLM supports the full spectrum of NVIDIA GPU architectures: -- **NVIDIA Blackwell**: B200, GB200, B300, GB300, DGX Spark -- **NVIDIA Hopper**: H100, H200, GH200 -- **NVIDIA Ada Lovelace**: L20, L40/L40S -- **NVIDIA Ampere**: A100 - ## What Can You Do With TensorRT LLM? Whether you're building the next generation of AI applications, optimizing existing LLM deployments, or exploring the frontiers of large language model technology, TensorRT LLM provides the tools, performance, and flexibility you need to succeed in the era of generative AI.To get started, refer to the {ref}`quick-start-guide`. diff --git a/docs/source/supported-hardware.md b/docs/source/supported-hardware.md new file mode 100644 index 000000000000..a8c96e99eeb2 --- /dev/null +++ b/docs/source/supported-hardware.md @@ -0,0 +1,7 @@ +# Supported Hardware + +TensorRT LLM supports the full spectrum of NVIDIA GPU architectures: +- **NVIDIA Blackwell**: B200, GB200, B300, GB300, DGX Spark +- **NVIDIA Hopper**: H100, H200, GH200 +- **NVIDIA Ada Lovelace**: L20, L40/L40S +- **NVIDIA Ampere**: A100