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 15, 04:45 UTC
[Doc] correct LoRA capitalization (#20135)
Signed-off-by: kyolebu <kyu@redhat.com>
Kyle Yu committed
Jun 26, 2025 at 18:22 UTC
07b8fae219b1fff51ef115c38c44b51395be5bb5
2 files changed
+2
-2
docs/README.md
+1
-1
@@ -40,7 +40,7 @@ vLLM is flexible and easy to use with:
40
- OpenAI-compatible API server
41
- Support NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs, Gaudi® accelerators and GPUs, IBM Power CPUs, TPU, and AWS Trainium and Inferentia Accelerators.
42
- Prefix caching support
43
-- Multi-lora support
43
+- Multi-LoRA support
44
45
For more information, check out the following:
46
docs/models/supported_models.md
+1
-1
@@ -427,7 +427,7 @@ Specified using `--task embed`.
427
See [relevant issue on HF Transformers](https://github.com/huggingface/transformers/issues/34882).
428
429
!!! note
430
- `jinaai/jina-embeddings-v3` supports multiple tasks through lora, while vllm temporarily only supports text-matching tasks by merging lora weights.
430
+ `jinaai/jina-embeddings-v3` supports multiple tasks through LoRA, while vllm temporarily only supports text-matching tasks by merging LoRA weights.
431
432
!!! note
433
The second-generation GTE model (mGTE-TRM) is named `NewModel`. The name `NewModel` is too generic, you should set `--hf-overrides '{"architectures": ["GteNewModel"]}'` to specify the use of the `GteNewModel` architecture.