A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Fix CLI parameter documentation inconsistency in pooling_models.md (#23630)
Raghavan committed
Aug 26, 2025 at 13:35 UTC
ff77764f868290bf746d101d3998095b73e7811d
1 file changed
+2
-2
docs/models/pooling_models.md
+2
-2
@@ -205,12 +205,12 @@ Our [OpenAI-Compatible Server](../serving/openai_compatible_server.md) provides
205
206
There is currently no official interface for specifying support for Matryoshka Embeddings. In vLLM, if `is_matryoshka` is `True` in `config.json,` it is allowed to change the output to arbitrary dimensions. Using `matryoshka_dimensions` can control the allowed output dimensions.
207
208
-For models that support Matryoshka Embeddings but not recognized by vLLM, please manually override the config using `hf_overrides={"is_matryoshka": True}`, `hf_overrides={"matryoshka_dimensions": [<allowed output dimensions>]}` (offline) or `--hf_overrides '{"is_matryoshka": true}'`, `--hf_overrides '{"matryoshka_dimensions": [<allowed output dimensions>]}'`(online).
208
+For models that support Matryoshka Embeddings but not recognized by vLLM, please manually override the config using `hf_overrides={"is_matryoshka": True}`, `hf_overrides={"matryoshka_dimensions": [<allowed output dimensions>]}` (offline) or `--hf-overrides '{"is_matryoshka": true}'`, `--hf-overrides '{"matryoshka_dimensions": [<allowed output dimensions>]}'`(online).
209
210
Here is an example to serve a model with Matryoshka Embeddings enabled.
211
212
```text
213
-vllm serve Snowflake/snowflake-arctic-embed-m-v1.5 --hf_overrides '{"matryoshka_dimensions":[256]}'
213
+vllm serve Snowflake/snowflake-arctic-embed-m-v1.5 --hf-overrides '{"matryoshka_dimensions":[256]}'
214
```
215
216
### Offline Inference