Update README.md

README.md

@@ -1,8 +1,8 @@
 ---
----
 license: other
 license_link: https://huggingface.co/stepfun-ai/Step-5-Preview/blob/main/LICENSE.txt
 ---
+
 <p align="center">
   <img src="https://cdn-uploads.huggingface.co/production/uploads/65dc9de42a6348b052a3286e/-R9DERgmQiBfO2cF0HXoD.png" alt="StepFun logo" width="64" />
 </p>
@@ -141,8 +141,6 @@ Run the serving commands below inside the container. If the checkpoint requires
 <details>
 <summary><strong>FP8: Single Node on 4 B300 GPUs</strong></summary>
 
-#### FP8: Single Node on 4 B300 GPUs
-
 Choose one of the following parallel configurations for a single node with four B300 GPUs:
 
 | Mode | Tensor parallel | Data parallel | Expert parallel |
@@ -248,8 +246,6 @@ TP and TEP use DP=1; DEP uses TP=1. In all configurations, `--max-num-seqs` appl
 <details>
 <summary><strong>BF16</strong></summary>
 
-#### BF16
-
 BF16 deployments require a BF16 checkpoint. Setting `--dtype bfloat16` on the FP8 checkpoint does not convert its quantized weights to BF16.
 
 Mount the BF16 checkpoint directory at the same path inside the container, then set `MODEL` to that path:
@@ -361,8 +357,6 @@ Use separate checkpoints and output directories for FP8 and BF16. Conversion pre
 <details>
 <summary><strong>FP8: One H200 Node, 8 GPUs</strong></summary>
 
-#### FP8: One H200 Node, 8 GPUs
-
 Convert the FP8 checkpoint once, then launch eight local processes for TP8 / EP8 generation:
 
 ```bash
@@ -389,8 +383,6 @@ torchrun --standalone --nproc-per-node=8 generate.py \
 <details>
 <summary><strong>BF16: Two H200 Nodes, 16 GPUs</strong></summary>
 
-#### BF16: Two H200 Nodes, 16 GPUs
-
 For TP16 / EP16 generation across two nodes, first convert the BF16 checkpoint into 16 shards. Make the resulting `tp16/` and `tokenizer_files/` directories accessible to both nodes:
 
 ```bash
@@ -433,6 +425,11 @@ This launches 16 processes across the two nodes, matching the 16-shard checkpoin
 
 ### SGLang
 
+| Framework | Precision | Hardware | Parallelism | Interface |
+| --- | --- | --- | --- | --- |
+| SGLang | FP8 | One B300 node, 4 GPUs | TP4/EP4 | OpenAI-compatible API |
+| SGLang | FP8 | One H200 node, 8 GPUs | TP8/EP8 | OpenAI-compatible API |
+
 #### Environment Setup
 
 Pull the Step 5 Preview SGLang Docker image:
@@ -441,14 +438,12 @@ Pull the Step 5 Preview SGLang Docker image:
 docker pull lmsysorg/sglang:step-5-preview
 ```
 
-Then, launch the server using the configuration for your hardware.
+Then, launch the server using the configuration for your hardware. For more optimized configurations, including MegaMoE, attention data parallelism and HiCache, see the [SGLang Cookbook for Step 5 Preview](https://docs.sglang.io/cookbook/autoregressive/StepFun/Step-5-Preview).
 
 <details>
-<summary><strong>B300: Low latency (4 GPUs, TP4/EP1)</strong></summary>
+<summary><strong>B300: TP4/EP4, 4 GPUs</strong></summary>
 
-#### B300: Low latency (4 GPUs, TP4/EP1)
-
-For single-user chat and latency-sensitive serving.
+Uses MegaMoE for the FP8 routed experts.
 
 ```bash
 export CUDA_VISIBLE_DEVICES=0,1,2,3
@@ -458,8 +453,9 @@ python -m sglang.launch_server \
   --model-path stepfun-ai/Step-5-Preview \
   --served-model-name step5 \
   --tp 4 \
-  --ep-size 1 \
+  --ep-size 4 \
   --moe-runner-backend flashinfer_trtllm \
+  --moe-a2a-backend megamoe \
   --attention-backend fa4 \
   --page-size 64 \
   --kv-cache-dtype bfloat16 \
@@ -474,19 +470,16 @@ python -m sglang.launch_server \
   --speculative-eagle-topk 1 \
   --speculative-num-draft-tokens 4 \
   --enable-multi-layer-eagle \
-  --reasoning-parser step3p5 \
-  --tool-call-parser step3p5 \
+  --reasoning-parser step5 \
+  --tool-call-parser step5 \
   --host 0.0.0.0 \
   --port 30000
 ```
 
 </details>
 
-
 <details>
-<summary><strong>H200: Balanced (8 GPUs, TP8/EP8)</strong></summary>
-
-#### H200: Balanced (8 GPUs, TP8/EP8)
+<summary><strong>H200: TP8/EP8, 8 GPUs</strong></summary>
 
 For single-node H200 serving with Triton MoE and FA3 attention.
 
@@ -514,8 +507,8 @@ python -m sglang.launch_server \
   --speculative-eagle-topk 1 \
   --speculative-num-draft-tokens 4 \
   --enable-multi-layer-eagle \
-  --reasoning-parser step3p5 \
-  --tool-call-parser step3p5 \
+  --reasoning-parser step5 \
+  --tool-call-parser step5 \
   --host 0.0.0.0 \
   --port 30000
 ```
@@ -554,6 +547,6 @@ curl http://127.0.0.1:18000/v1/chat/completions \
 
 ## License
 
-This model, including its weights, parameters, configuration, tokenizer, model-specific code, and documentation, is licensed under the StepFun Model License 1.0. The full text of the License is available in the [LICENSE](LICENSE) file in this repository. The StepFun Model License 1.0 is an Apache-2.0-Style license, with additional attribution and commercial-license conditions specific to model use, modification and distribution.
+This model, including its weights, parameters, configuration, tokenizer, model-specific code, and documentation, is licensed under the StepFun Model License 1.0. The full text of the License is available in the [LICENSE.txt](https://huggingface.co/stepfun-ai/Step-5-Preview/blob/main/LICENSE.txt) file in this repository. The StepFun Model License 1.0 is an Apache-2.0-Style license, with additional attribution and commercial-license conditions specific to model use, modification and distribution.
 
 Where accompanying materials in this repository, including sample code, datasets, third-party components and other documentation, are separately marked as subject to a different license, such materials are licensed under that license.