EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[Doc] Add experimental tag for flashinfer mla (#3925)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-02-27 01:55:36 -08:00
committed by GitHub
parent d8a98a2cad
commit 3e02526b1f
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/backend/server_arguments.md
View File

@@ -133,7 +133,7 @@ Please consult the documentation below to learn more about the parameters you ma
* `attention_backend`: The backend for attention computation and KV cache management.
* `sampling_backend`: The backend for sampling.
* `enable_flashinfer_mla`: The backend for flashinfer MLA wrapper. It can optimize the throughput of deepseek models.
* `enable_flashinfer_mla`: The backend for flashinfer MLA wrapper that accelerates deepseek models. (In Experiment Stage)
## Constrained Decoding

2
docs/references/deepseek.md
View File

@@ -85,7 +85,7 @@ Please refer to [the example](https://github.com/sgl-project/sglang/tree/main/be
- **Weight Absorption**: By applying the associative law of matrix multiplication to reorder computation steps, this method balances computation and memory access and improves efficiency in the decoding phase.
- **Flashinfer MLA Wrapper**: By providing `--enable-flashinfer-mla` argument, the server will use MLA kernels customized by Flashinfer. This optimization can be significant under long context scenarios. More details can be referred to [this document](https://docs.flashinfer.ai/api/mla.html).
- **Flashinfer MLA Wrapper**: By providing `--enable-flashinfer-mla` argument, the server will use MLA kernels customized by Flashinfer. More details can be referred to [this document](https://docs.flashinfer.ai/api/mla.html). (In Experiment Stage)
- **FP8 Quantization**: W8A8 FP8 and KV Cache FP8 quantization enables efficient FP8 inference. Additionally, we have implemented Batched Matrix Multiplication (BMM) operator to facilitate FP8 inference in MLA with weight absorption.