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

Improve supported models doc (#6430)

Browse Source
This commit is contained in:
simveit
2025-05-19 19:43:35 +02:00
committed by GitHub
parent 844e2f227a
commit 506e5de8fe
4 changed files with 21 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/supported_models/embedding_models.md
View File

@@ -43,7 +43,7 @@ print("Embeddings:", [x.get("embedding") for x in response.get("data", [])])
```
## Supporting Matrixs
## Supported models
| Model Family (Embedding) | Example HuggingFace Identifier | Chat Template | Description |
|-------------------------------------------------|-----------------------------------------------|---------------|--------------------------------------------------------------------------------------------------------------------------------------|

9
docs/supported_models/generative_models.md
View File

@@ -11,8 +11,15 @@ python3 -m sglang.launch_server \
--port 30000 \
```
## Supporting Matrixs
## Supported models
Below the supported models are summarized in a table.
If unsure if a specific architecture is implemented you may look it up via github search for example to search for `Qwen3ForCausalLm` use the expression
```
repo:sgl-project/sglang path:/^python\/sglang\/srt\/models\// Qwen3ForCausalLm
```
in Github search.
| Model Family (Variants) | Example HuggingFace Identifier | Description |
|-------------------------------------|--------------------------------------------------|----------------------------------------------------------------------------------------|

14
docs/supported_models/multimodal_language_models.md
View File

@@ -1,7 +1,6 @@
# Multimodal Language Models
These models accept multi-modal inputs (e.g., images and text) and generate text output. They augment language models
with multimodal encoders.
These models accept multi-modal inputs (e.g., images and text) and generate text output. They augment language models with multimodal encoders.
## Example launch Command
@@ -12,7 +11,16 @@ python3 -m sglang.launch_server \
--port 30000 \
```
## Supporting Metrics
## Supported models
Below the supported models are summarized in a table.
If unsure if a specific architecture is implemented you may look it up via Github search. For example to search for `Qwen2_5_VLForConditionalGeneration` use the expression
```
repo:sgl-project/sglang path:/^python\/sglang\/srt\/models\// Qwen2_5_VLForConditionalGeneration
```
in Github search.
| Model Family (Variants) | Example HuggingFace Identifier | Chat Template | Description |
|----------------------------|--------------------------------------------|------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|

2
docs/supported_models/reward_models.md
View File

@@ -17,7 +17,7 @@ python3 -m sglang.launch_server \
--port 30000 \
```
## Supporting Matrixs
## Supported models
| Model Family (Reward) | Example HuggingFace Identifier | Description |
|---------------------------------------------------------------------------|-----------------------------------------------------|---------------------------------------------------------------------------------|