From 133ce9ac56e88902aafcf423e3de521dc613826c Mon Sep 17 00:00:00 2001
From: Meng Zhang <meng@tabbyml.com>
Date: Wed, 30 Aug 2023 23:09:23 +0800
Subject: [PATCH] docs: add faq.md (#381)

* docs: add 03-faq.md

* docs: add section on reduced precision inference compute capability

* update
---
 ...ting-started.md => 01-gettings-started.md} |  0
 .../01-docker.mdx                             |  0
 .../02-apple.md                               |  0
 .../02-self-hosting.md}                       |  0
 website/docs/03-faq.md                        | 20 +++++++++++++++++++
 5 files changed, 20 insertions(+)
 rename website/docs/{getting-started.md => 01-gettings-started.md} (100%)
 rename website/docs/{self-hosting => 02-self-hosting}/01-docker.mdx (100%)
 rename website/docs/{self-hosting => 02-self-hosting}/02-apple.md (100%)
 rename website/docs/{self-hosting/self-hosting.md => 02-self-hosting/02-self-hosting.md} (100%)
 create mode 100644 website/docs/03-faq.md

diff --git a/website/docs/getting-started.md b/website/docs/01-gettings-started.md
similarity index 100%
rename from website/docs/getting-started.md
rename to website/docs/01-gettings-started.md
diff --git a/website/docs/self-hosting/01-docker.mdx b/website/docs/02-self-hosting/01-docker.mdx
similarity index 100%
rename from website/docs/self-hosting/01-docker.mdx
rename to website/docs/02-self-hosting/01-docker.mdx
diff --git a/website/docs/self-hosting/02-apple.md b/website/docs/02-self-hosting/02-apple.md
similarity index 100%
rename from website/docs/self-hosting/02-apple.md
rename to website/docs/02-self-hosting/02-apple.md
diff --git a/website/docs/self-hosting/self-hosting.md b/website/docs/02-self-hosting/02-self-hosting.md
similarity index 100%
rename from website/docs/self-hosting/self-hosting.md
rename to website/docs/02-self-hosting/02-self-hosting.md
diff --git a/website/docs/03-faq.md b/website/docs/03-faq.md
new file mode 100644
index 0000000..9edb500
--- /dev/null
+++ b/website/docs/03-faq.md
@@ -0,0 +1,20 @@
+# Frequently Asked Questions
+
+<details>
+  <summary>How much VRAM a LLM model consumes?</summary>
+  <div>By default, Tabby operates in int8 mode with CUDA, requiring approximately 8GB of VRAM for CodeLlama-7B.</div>
+</details>
+
+<details>
+  <summary>What GPUs are required for reduced-precision inference (e.g int8)?</summary>
+  <div>
+    <ul>
+      <li>int8: Compute Capability >= 7.0 or Compute Capability 6.1</li>
+      <li>float16: Compute Capability >= 7.0</li>
+      <li>bfloat16: Compute Capability >= 8.0</li>
+    </ul>
+    <p>
+      To determine the mapping between the GPU card type and its compute capability, please visit <a href="https://developer.nvidia.com/cuda-gpus">this page</a>
+    </p>
+  </div>
+</details>