From bcecf27e7ca265ec851746d84f5889e22b4b5813 Mon Sep 17 00:00:00 2001 From: Baizhou Zhang Date: Sat, 25 Oct 2025 15:07:50 -0700 Subject: [PATCH] [Doc] Fix format for deepseek v3.2 document (#12130) --- docs/basic_usage/deepseek_v32.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/basic_usage/deepseek_v32.md b/docs/basic_usage/deepseek_v32.md index bac87498b..4255a2bbf 100644 --- a/docs/basic_usage/deepseek_v32.md +++ b/docs/basic_usage/deepseek_v32.md @@ -60,7 +60,7 @@ python -m sglang.launch_server --model deepseek-ai/DeepSeek-V3.2-Exp --tp 8 --ep - B200: `flashmla_kv` prefill attention, `flashmla_kv` decode attention, `fp8_e4m3` kv cache dtype. - Currently we don't enable `prefill=flashmla_sparse` with `decode=flashmla_kv` due to latency caused by kv cache quantization operations. In the future we might shift to this setting after attention/quantization kernels are optimized. -### Multi-token Prediction +## Multi-token Prediction SGLang implements Multi-Token Prediction (MTP) for DeepSeek V3.2 based on [EAGLE speculative decoding](https://docs.sglang.ai/advanced_features/speculative_decoding.html#EAGLE-Decoding). With this optimization, the decoding speed can be improved significantly on small batch sizes. Please look at [this PR](https://github.com/sgl-project/sglang/pull/11652) for more information. Example usage: @@ -71,10 +71,10 @@ python -m sglang.launch_server --model deepseek-ai/DeepSeek-V3.2-Exp --tp 8 --dp - The default value of `--max-running-requests` is set to `48` for MTP. For larger batch sizes, this value should be increased beyond the default value. -# Function Calling and Reasoning Parser +## Function Calling and Reasoning Parser The usage of function calling and reasoning parser is the same as DeepSeek V3.1. Please refer to [Reasoning Parser](https://docs.sglang.ai/advanced_features/separate_reasoning.html) and [Tool Parser](https://docs.sglang.ai/advanced_features/tool_parser.html) documents. -# PD Disaggregation +## PD Disaggregation Prefill Command: ```bash