Merge branch 'main' into transformers-backend

OK

Author: ariG23498

Gemfile

@@ -1,3 +1,6 @@
 source "https://rubygems.org"
 
-gem "github-pages", "~> 232", group: :jekyll_plugins
+group :jekyll_plugins do
+    gem "github-pages", "~> 232"
+    gem "jekyll-gfm-admonitions", '~> 1.2'
+end

Gemfile.lock

@@ -27,6 +27,7 @@ GEM
     commonmarker (0.23.11)
     concurrent-ruby (1.3.5)
     connection_pool (2.5.0)
+    cssminify (1.0.2)
     csv (3.3.2)
     dnsruby (1.72.3)
       base64 (~> 0.2.0)
@@ -138,6 +139,10 @@ GEM
       jekyll (>= 3.0, < 5.0)
     jekyll-feed (0.17.0)
       jekyll (>= 3.7, < 5.0)
+    jekyll-gfm-admonitions (1.2.0)
+      cssminify (~> 1.0)
+      jekyll (>= 3.0, < 5.0)
+      octicons (~> 19.8)
     jekyll-gist (1.5.0)
       octokit (~> 4.2)
     jekyll-github-metadata (2.16.1)
@@ -239,6 +244,7 @@ GEM
       racc (~> 1.4)
     nokogiri (1.18.4-x86_64-linux-gnu)
       racc (~> 1.4)
+    octicons (19.15.1)
     octokit (4.25.1)
       faraday (>= 1, < 3)
       sawyer (~> 0.9)
@@ -275,10 +281,12 @@ GEM
 
 PLATFORMS
   arm64-darwin
+  arm64-darwin-24
   x86_64-linux
 
 DEPENDENCIES
   github-pages (~> 232)
+  jekyll-gfm-admonitions (~> 1.2)
 
 BUNDLED WITH
    2.6.2

README.md

@@ -31,6 +31,30 @@ math block
 $$
 ```
 
+## GitHub Flavored Admonitions
+
+The blog supports GitHub flavored admonitions via [jekyll-gfm-admonition](https://github.com/Helveg/jekyll-gfm-admonitions). It supports the following syntax:
+
+```markdown
+> [!NOTE]
+> Highlights information that users should take into account, even when skimming.
+> And supports multi-line text.
+
+> [!TIP]
+> Optional information to help a user be more successful.
+
+> [!IMPORTANT]
+> Crucial information necessary for users to succeed.
+
+> [!WARNING]
+> Critical content demanding immediate
+> user attention due to potential risks.
+
+> [!CAUTION]
+> Negative potential consequences of an action.
+> Opportunity to provide more context.
+```
+
 ## Theme customization
 
 The theme we are using is [Minima](https://github.com/jekyll/minima). If you need to customise anything from this theme, see [Overriding theme defaults](https://jekyllrb.com/docs/themes/#overriding-theme-defaults).

_config.yml

@@ -17,6 +17,7 @@ remote_theme: jekyll/minima@5ce4006d175e6e5278bb63a0aad1a85e3bf2370b
 plugins:
   - jekyll-feed
   - jekyll-seo-tag
+  - jekyll-gfm-admonitions
 
 # Theme-specific settings
 

_posts/2025-04-05-llama4.md

@@ -72,7 +72,6 @@ While more performance enhancements are on the way, we believe the Llama 4 model
 
 * **Boost Performance & Context Length:** Set `--kv-cache-dtype fp8` to potentially double the usable context window and gain a performance boost. We observe little to no accuracy drop in relevant evaluations with this setting.
 * **Maximize Context Window (up to 10M):** To fully utilize the maximum context windows (up to 10M for Scout), we recommend serving across multiple nodes using tensor parallelism or pipeline parallelism. Follow our distributed inference guide [here](https://docs.vllm.ai/en/latest/serving/distributed_serving.html).
-* **Improve Long Context Accuracy (\>32K):** We highly recommend adding `--override-generation-config='{"attn_temperature_tuning": true}'` to improve accuracy for contexts longer than 32K tokens.
 
 **Other Hardware Support & Quantizations:**