minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Doc] Fix format for deepseek v3.2 document (#12130)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-10-25 15:07:50 -07:00
committed by GitHub
parent 4b0ac1d52a
commit bcecf27e7c
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/basic_usage/deepseek_v32.md
+3 -3
View File
@@ -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. - 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. - 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. 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: 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. - 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. 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: Prefill Command:
```bash ```bash