docs: expand model grid to 26 cards, 40 architectures (24 families)

Author: dndungu

content/_index.html

@@ -487,7 +487,7 @@ <h3 style="font-size:1rem;font-weight:600;margin-bottom:16px">Performance journe
   <div class="wrap">
     <div class="section-head">
       <h2>Supported models</h2>
-      <p>28 architectures across 16 model families. Load any GGUF model from HuggingFace.</p>
+      <p>40 architectures across 24 model families. Load any GGUF model from HuggingFace.</p>
     </div>
     <div class="model-grid">
       <div class="model-card"><div class="name">Gemma 3/3n</div><div class="status prod">Transformer</div></div>
@@ -508,6 +508,14 @@ <h2>Supported models</h2>
       <div class="model-card"><div class="name">LLaVA/Qwen-VL</div><div class="status prod">Vision-language</div></div>
       <div class="model-card"><div class="name">BERT</div><div class="status prod">Encoder</div></div>
       <div class="model-card"><div class="name">Granite TS</div><div class="status prod">Time series</div></div>
+      <div class="model-card"><div class="name">GLM-4/ChatGLM</div><div class="status prod">Transformer + MoE</div></div>
+      <div class="model-card"><div class="name">Kimi K2</div><div class="status prod">Linear attention MoE</div></div>
+      <div class="model-card"><div class="name">LFM2</div><div class="status prod">Hybrid MoE</div></div>
+      <div class="model-card"><div class="name">OLMo 2</div><div class="status prod">Transformer</div></div>
+      <div class="model-card"><div class="name">EXAONE</div><div class="status prod">Transformer</div></div>
+      <div class="model-card"><div class="name">StarCoder 2</div><div class="status prod">Code generation</div></div>
+      <div class="model-card"><div class="name">InternLM 2</div><div class="status prod">Transformer</div></div>
+      <div class="model-card"><div class="name">DBRX</div><div class="status prod">Fine-grained MoE</div></div>
     </div>
     <div style="text-align:center;margin-top:32px">
       <p style="color:var(--fg3);font-size:.875rem">Uses GGUF as the sole model format. Compatible with llama.cpp, Ollama, LM Studio, and GPT4All model files.</p>

content/docs/reference/migration-v1.md

@@ -236,7 +236,7 @@ for usage of deprecated symbols.
 These are additive and do not require migration, but are worth knowing about:
 
 - **Architecture registry** -- `inference.RegisterArchitecture` / `inference.ListArchitectures` for pluggable model support.
-- **28 architectures (16 model families)** -- Llama 3/4, Gemma 3/3n, Mistral, Qwen 2, Phi 3/4, DeepSeek V3, GPT-2, Nemotron-H, MiniMax M2, Falcon, Command R, Mixtral, RWKV, Jamba, Mamba 3, Whisper, and more.
+- **28 architectures (16 model families)** -- Llama 3/4, Gemma 3/3n, Mistral, Qwen 2, Phi 3/4, DeepSeek V3, GPT-2, Nemotron-H, MiniMax M2, GLM-4, Kimi K2, LFM2, OLMo 2, EXAONE, StarCoder 2, InternLM 2, DBRX, Falcon, Command R, Mixtral, RWKV, Jamba, Mamba 3, Whisper, and more.
 - **Speculative decoding** -- `inference.Model.SpeculativeGenerate` and `generate.WithSpeculativeDraft`.
 - **Paged KV cache** -- `generate.WithPagedKV` for memory-efficient serving.
 - **Prefix caching** -- `generate.WithPrefixCache` for shared system prompt reuse.