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

[feat] add ascend readme and docker release (#8700)

Browse Source 
Signed-off-by: mywaaagh_admin <pkwarcraft@gmail.com>
Signed-off-by: lichaoran <pkwarcraft@gmail.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
li chaoran
2025-08-13 04:25:42 +08:00
committed by GitHub
parent 305b27c124
commit 2ecbd8b8bf
7 changed files with 467 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/basic_usage/deepseek.md
View File

@@ -24,6 +24,7 @@ To run DeepSeek V3/R1 models, the requirements are as follows:
| **Quantized weights (int8)** | 16 x A100/800 |
| | 32 x L40S |
| | Xeon 6980P CPU |
| | 2 x Atlas 800I A3 |
<style>
.md-typeset__table {
@@ -64,6 +65,7 @@ Detailed commands for reference:
- [16 x A100 (int8)](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-16-a100a800-with-int8-quantization)
- [32 x L40S (int8)](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-32-l40s-with-int8-quantization)
- [Xeon 6980P CPU](../platforms/cpu_server.md#example-running-deepseek-r1)
- [2 x Atlas 800I A3 (int8)](../platforms/ascend_npu.md#running-deepseek-v3)
### Download Weights
If you encounter errors when starting the server, ensure the weights have finished downloading. It's recommended to download them beforehand or restart multiple times until all weights are downloaded. Please refer to [DeepSeek V3](https://huggingface.co/deepseek-ai/DeepSeek-V3-Base#61-inference-with-deepseek-infer-demo-example-only) official guide to download the weights.