xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 02:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add docs for runai_streamer_sharded (#17093)

Browse Source 
Signed-off-by: Omer Dayan (SW-GPU) <omer@run.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
omer-dayan 2025-04-24 11:03:21 +03:00 committed by GitHub
parent 9c1244de57
commit 2bc0f72ae5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docs/source/models/extensions/runai_model_streamer.md
View File

@ -51,3 +51,29 @@ vllm serve /home/meta-llama/Llama-3.2-3B-Instruct --load-format runai_streamer -
:::{note}
For further instructions about tunable parameters and additional parameters configurable through environment variables, read the [Environment Variables Documentation](https://github.com/run-ai/runai-model-streamer/blob/master/docs/src/env-vars.md).
:::
## Sharded Model Loading
vLLM also supports loading sharded models using Run:ai Model Streamer. This is particularly useful for large models that are split across multiple files. To use this feature, use the `--load-format runai_streamer_sharded` flag:
```console
vllm serve /path/to/sharded/model --load-format runai_streamer_sharded
```
The sharded loader expects model files to follow the same naming pattern as the regular sharded state loader: `model-rank-{rank}-part-{part}.safetensors`. You can customize this pattern using the `pattern` parameter in `--model-loader-extra-config`:
```console
vllm serve /path/to/sharded/model --load-format runai_streamer_sharded --model-loader-extra-config '{"pattern":"custom-model-rank-{rank}-part-{part}.safetensors"}'
```
To create sharded model files, you can use the script provided in <gh-file:examples/offline_inference/save_sharded_state.py>. This script demonstrates how to save a model in the sharded format that is compatible with the Run:ai Model Streamer sharded loader.
The sharded loader supports all the same tunable parameters as the regular Run:ai Model Streamer, including `concurrency` and `memory_limit`. These can be configured in the same way:
```console
vllm serve /path/to/sharded/model --load-format runai_streamer_sharded --model-loader-extra-config '{"concurrency":16, "memory_limit":5368709120}'
```
:::{note}
The sharded loader is particularly efficient for tensor or pipeline parallel models where each worker only needs to read its own shard rather than the entire checkpoint.
:::