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, 03:30 UTC
fix[Docs]: link anchor is incorrect #20309 (#20315)
Signed-off-by: zxw <1020938856@qq.com>
yyzxw committed
Jul 2, 2025 at 14:32 UTC
be0cfb2b680b59b8521024f1c6e5d18dbe08677e
8 files changed
+10
-10
docs/configuration/engine_args.md
+1
-1
@@ -6,7 +6,7 @@ title: Engine Arguments
6
Engine arguments control the behavior of the vLLM engine.
7
8
- For [offline inference][offline-inference], they are part of the arguments to [LLM][vllm.LLM] class.
9
-- For [online serving][openai-compatible-server], they are part of the arguments to `vllm serve`.
9
+- For [online serving][serving-openai-compatible-server], they are part of the arguments to `vllm serve`.
10
11
You can look at [EngineArgs][vllm.engine.arg_utils.EngineArgs] and [AsyncEngineArgs][vllm.engine.arg_utils.AsyncEngineArgs] to see the available engine arguments.
12
docs/design/arch_overview.md
+1
-1
@@ -74,7 +74,7 @@ python -m vllm.entrypoints.openai.api_server --model <model>
74
75
That code can be found in <gh-file:vllm/entrypoints/openai/api_server.py>.
76
77
-More details on the API server can be found in the [OpenAI-Compatible Server][openai-compatible-server] document.
77
+More details on the API server can be found in the [OpenAI-Compatible Server][serving-openai-compatible-server] document.
78
79
## LLM Engine
80
docs/features/structured_outputs.md
+1
-1
@@ -21,7 +21,7 @@ The following parameters are supported, which must be added as extra parameters:
21
- `guided_grammar`: the output will follow the context free grammar.
22
- `structural_tag`: Follow a JSON schema within a set of specified tags within the generated text.
23
24
-You can see the complete list of supported parameters on the [OpenAI-Compatible Server][openai-compatible-server] page.
24
+You can see the complete list of supported parameters on the [OpenAI-Compatible Server][serving-openai-compatible-server] page.
25
26
Structured outputs are supported by default in the OpenAI-Compatible Server. You
27
may choose to specify the backend to use by setting the
docs/getting_started/installation/intel_gaudi.md
+1
-1
@@ -110,7 +110,7 @@ docker run \
110
### Supported features
111
112
- [Offline inference][offline-inference]
113
-- Online serving via [OpenAI-Compatible Server][openai-compatible-server]
113
+- Online serving via [OpenAI-Compatible Server][serving-openai-compatible-server]
114
- HPU autodetection - no need to manually select device within vLLM
115
- Paged KV cache with algorithms enabled for Intel Gaudi accelerators
116
- Custom Intel Gaudi implementations of Paged Attention, KV cache ops,
docs/models/generative_models.md
+1
-1
@@ -134,7 +134,7 @@ outputs = llm.chat(conversation, chat_template=custom_template)
134
135
## Online Serving
136
137
-Our [OpenAI-Compatible Server][openai-compatible-server] provides endpoints that correspond to the offline APIs:
137
+Our [OpenAI-Compatible Server][serving-openai-compatible-server] provides endpoints that correspond to the offline APIs:
138
139
- [Completions API][completions-api] is similar to `LLM.generate` but only accepts text.
140
- [Chat API][chat-api] is similar to `LLM.chat`, accepting both text and [multi-modal inputs][multimodal-inputs] for models with a chat template.
docs/models/pooling_models.md
+1
-1
@@ -113,7 +113,7 @@ A code example can be found here: <gh-file:examples/offline_inference/basic/scor
113
114
## Online Serving
115
116
-Our [OpenAI-Compatible Server][openai-compatible-server] provides endpoints that correspond to the offline APIs:
116
+Our [OpenAI-Compatible Server][serving-openai-compatible-server] provides endpoints that correspond to the offline APIs:
117
118
- [Pooling API][pooling-api] is similar to `LLM.encode`, being applicable to all types of pooling models.
119
- [Embeddings API][embeddings-api] is similar to `LLM.embed`, accepting both text and [multi-modal inputs][multimodal-inputs] for embedding models.
docs/models/supported_models.md
+3
-3
@@ -34,7 +34,7 @@ llm.apply_model(lambda model: print(type(model)))
34
If it is `TransformersForCausalLM` then it means it's based on Transformers!
35
36
!!! tip
37
- You can force the use of `TransformersForCausalLM` by setting `model_impl="transformers"` for [offline-inference][offline-inference] or `--model-impl transformers` for the [openai-compatible-server][openai-compatible-server].
37
+ You can force the use of `TransformersForCausalLM` by setting `model_impl="transformers"` for [offline-inference][offline-inference] or `--model-impl transformers` for the [openai-compatible-server][serving-openai-compatible-server].
38
39
!!! note
40
vLLM may not fully optimise the Transformers implementation so you may see degraded performance if comparing a native model to a Transformers model in vLLM.
@@ -53,8 +53,8 @@ For a model to be compatible with the Transformers backend for vLLM it must:
53
54
If the compatible model is:
55
56
-- on the Hugging Face Model Hub, simply set `trust_remote_code=True` for [offline-inference][offline-inference] or `--trust-remote-code` for the [openai-compatible-server][openai-compatible-server].
57
-- in a local directory, simply pass directory path to `model=<MODEL_DIR>` for [offline-inference][offline-inference] or `vllm serve <MODEL_DIR>` for the [openai-compatible-server][openai-compatible-server].
56
+- on the Hugging Face Model Hub, simply set `trust_remote_code=True` for [offline-inference][offline-inference] or `--trust-remote-code` for the [openai-compatible-server][serving-openai-compatible-server].
57
+- in a local directory, simply pass directory path to `model=<MODEL_DIR>` for [offline-inference][offline-inference] or `vllm serve <MODEL_DIR>` for the [openai-compatible-server][serving-openai-compatible-server].
58
59
This means that, with the Transformers backend for vLLM, new models can be used before they are officially supported in Transformers or vLLM!
60
docs/serving/openai_compatible_server.md
+1
-1
@@ -1,7 +1,7 @@
1
---
2
title: OpenAI-Compatible Server
3
---
4
-[](){ #openai-compatible-server }
4
+[](){ #serving-openai-compatible-server }
5
6
vLLM provides an HTTP server that implements OpenAI's [Completions API](https://platform.openai.com/docs/api-reference/completions), [Chat API](https://platform.openai.com/docs/api-reference/chat), and more! This functionality lets you serve models and interact with them using an HTTP client.
7