DeepSeek/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3 synced 2025-01-22 12:25:30 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #33 from zhyncs/main

Browse Source 
docs: update SGLang usage
This commit is contained in:
Haswell Iris 2024-12-30 14:37:38 +08:00 committed by GitHub
commit 94410f8d58
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -227,7 +227,7 @@ We also provide OpenAI-Compatible API at DeepSeek Platform: [platform.deepseek.c
DeepSeek-V3 can be deployed locally using the following hardware and open-source community software: DeepSeek-V3 can be deployed locally using the following hardware and open-source community software:
1. **DeepSeek-Infer Demo**: We provide a simple and lightweight demo for FP8 and BF16 inference. 1. **DeepSeek-Infer Demo**: We provide a simple and lightweight demo for FP8 and BF16 inference.
2. **SGLang**: Fully support the DeepSeek-V3 model in both BF16 and FP8 inference modes. 2. **SGLang**: Fully support the DeepSeek-V3 model in both BF16 and FP8 inference modes, with Multi-Token Prediction [coming soon](https://github.com/sgl-project/sglang/issues/2591).
3. **LMDeploy**: Enables efficient FP8 and BF16 inference for local and cloud deployment. 3. **LMDeploy**: Enables efficient FP8 and BF16 inference for local and cloud deployment.
4. **TensorRT-LLM**: Currently supports BF16 inference and INT4/8 quantization, with FP8 support coming soon. 4. **TensorRT-LLM**: Currently supports BF16 inference and INT4/8 quantization, with FP8 support coming soon.
5. **vLLM**: Support DeekSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism. 5. **vLLM**: Support DeekSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism.
@ -288,10 +288,14 @@ torchrun --nnodes 2 --nproc-per-node 8 generate.py --node-rank $RANK --master-ad
### 6.2 Inference with SGLang (recommended) ### 6.2 Inference with SGLang (recommended)
[SGLang](https://github.com/sgl-project/sglang) currently supports MLA optimizations, FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering state-of-the-art latency and throughput performance among open-source frameworks. [SGLang](https://github.com/sgl-project/sglang) currently supports [MLA optimizations](https://lmsys.org/blog/2024-09-04-sglang-v0-3/#deepseek-multi-head-latent-attention-mla-throughput-optimizations), [DP Attention](https://lmsys.org/blog/2024-12-04-sglang-v0-4/#data-parallelism-attention-for-deepseek-models), FP8 (W8A8), FP8 KV Cache, and Torch Compile, delivering state-of-the-art latency and throughput performance among open-source frameworks.
Notably, [SGLang v0.4.1](https://github.com/sgl-project/sglang/releases/tag/v0.4.1) fully supports running DeepSeek-V3 on both **NVIDIA and AMD GPUs**, making it a highly versatile and robust solution. Notably, [SGLang v0.4.1](https://github.com/sgl-project/sglang/releases/tag/v0.4.1) fully supports running DeepSeek-V3 on both **NVIDIA and AMD GPUs**, making it a highly versatile and robust solution.
SGLang also supports [multi-node tensor parallelism](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3#example-serving-with-2-h208), enabling you to run this model on multiple network-connected machines.
Multi-Token Prediction (MTP) is in development, and progress can be tracked in the [optimization plan](https://github.com/sgl-project/sglang/issues/2591).
Here are the launch instructions from the SGLang team: https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3 Here are the launch instructions from the SGLang team: https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3
### 6.3 Inference with LMDeploy (recommended) ### 6.3 Inference with LMDeploy (recommended)