diff --git a/README.md b/README.md
index 3ae194934..0553ab853 100644
--- a/README.md
+++ b/README.md
@@ -20,10 +20,10 @@
 | [**Slides**](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides) |
 
 ## News
+- [2025/12] SGLang provides day-0 support for latest open models ([MiNo-V2](https://lmsys.org/blog/2025-12-16-mimo-v2-flash/), [Nemotron 3 Nano](https://lmsys.org/blog/2025-12-15-run-nvidia-nemotron-3-nano/), [Mistral Large 3](https://github.com/sgl-project/sglang/pull/14213), [LLaDA 2.0 Diffusion LLM](https://x.com/lmsysorg/status/1999378073125552375?s=20), [MiniMax M2](https://lmsys.org/blog/2025-11-04-miminmax-m2/)).
 - [2025/11] 🔥 SGLang Diffusion accelerates video and image generation ([blog](https://lmsys.org/blog/2025-11-07-sglang-diffusion/)).
 - [2025/10] 🔥 SGLang now runs natively on TPU with the SGLang-Jax backend ([blog](https://lmsys.org/blog/2025-10-29-sglang-jax/)).
-- [2025/10] PyTorch Conference 2025 SGLang Talk ([slide](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/sglang_pytorch_2025.pdf)).
-- [2025/09] 🔥 Deploying DeepSeek on GB200 NVL72 with PD and Large Scale EP (Part II): 3.8x Prefill, 4.8x Decode Throughput ([blog](https://lmsys.org/blog/2025-09-25-gb200-part-2/)).
+- [2025/09] Deploying DeepSeek on GB200 NVL72 with PD and Large Scale EP (Part II): 3.8x Prefill, 4.8x Decode Throughput ([blog](https://lmsys.org/blog/2025-09-25-gb200-part-2/)).
 - [2025/09] SGLang Day 0 Support for DeepSeek-V3.2 with Sparse Attention ([blog](https://lmsys.org/blog/2025-09-29-deepseek-V32/)).
 - [2025/08] SGLang x AMD SF Meetup on 8/22: Hands-on GPU workshop, tech talks by AMD/xAI/SGLang, and networking ([Roadmap](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_sglang_roadmap.pdf), [Large-scale EP](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_sglang_ep.pdf), [Highlights](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_highlights.pdf), [AITER/MoRI](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_aiter_mori.pdf), [Wave](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_wave.pdf)).
 - [2025/08] SGLang provides day-0 support for OpenAI gpt-oss model ([instructions](https://github.com/sgl-project/sglang/issues/8833))
@@ -32,6 +32,7 @@
 <details>
 <summary>More</summary>
 
+- [2025/10] PyTorch Conference 2025 SGLang Talk ([slide](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/sglang_pytorch_2025.pdf)).
 - [2025/10] SGLang x Nvidia SF Meetup on 10/2 ([recap](https://x.com/lmsysorg/status/1975339501934510231)).
 - [2025/06] SGLang, the high-performance serving infrastructure powering trillions of tokens daily, has been awarded the third batch of the Open Source AI Grant by a16z ([a16z blog](https://a16z.com/advancing-open-source-ai-through-benchmarks-and-bold-experimentation/)).
 - [2025/06] Deploying DeepSeek on GB200 NVL72 with PD and Large Scale EP (Part I): 2.7x Higher Decoding Throughput ([blog](https://lmsys.org/blog/2025-06-16-gb200-part-1/)).
diff --git a/python/sglang/srt/managers/scheduler.py b/python/sglang/srt/managers/scheduler.py
index e491e41e4..a58219ce7 100644
--- a/python/sglang/srt/managers/scheduler.py
+++ b/python/sglang/srt/managers/scheduler.py
@@ -292,13 +292,8 @@ class Scheduler(
             )
         )
 
-        # Init model config
-        self.model_config = ModelConfig.from_server_args(server_args)
-        self.dllm_config = (  # For diffusion LLM
-            DllmConfig.from_server_args(server_args)
-            if server_args.dllm_algorithm is not None
-            else None
-        )
+        # Init model configs
+        self.init_model_config()
 
         # Init metrics stats
         self.init_metrics(tp_rank, pp_rank, dp_rank)
@@ -306,7 +301,7 @@ class Scheduler(
         # Init inter-process communication
         self.init_sockets(server_args, port_args)
 
-        # Init pdmux context
+        # Init PD-multiplexing context
         if self.enable_pdmux:
             self.init_pdmux()
 
@@ -316,10 +311,10 @@ class Scheduler(
         # Init moe config and GEMM config (FP8 GEMM, etc.)
         self.init_moe_gemm_config()
 
-        # Launch a tensor parallel worker
+        # Launch a model worker and draft model worker if using speculative decoding
         self.init_model_worker()
 
-        # Init cache using the existing memory pool
+        # Init cache and memory pool
         self.init_cache_with_memory_pool()
 
         # Init running status
@@ -340,10 +335,10 @@ class Scheduler(
         # Init profiler
         self.init_profiler()
 
-        # Init disaggregation
+        # Init prefill-decodedisaggregation
         self.init_disaggregation()
 
-        # Init overlap
+        # Init overlap schedule
         self.init_overlap()
 
         # Init prefill kv split size when deterministic inference is enabled with various attention backends
@@ -352,6 +347,14 @@ class Scheduler(
         # Init request dispatcher
         self.init_request_dispatcher()
 
+    def init_model_config(self):
+        self.model_config = ModelConfig.from_server_args(self.server_args)
+        self.dllm_config = (  # For diffusion LLM
+            DllmConfig.from_server_args(self.server_args)
+            if self.server_args.dllm_algorithm is not None
+            else None
+        )
+
     def init_sockets(self, server_args: ServerArgs, port_args: PortArgs):
         context = zmq.Context(2)
         self.idle_sleeper = None