From 522ce30a85aadae92068910ba674bda888177e21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B1=AA=E5=BF=97=E9=B9=8F?= Date: Fri, 5 Dec 2025 00:43:28 +0800 Subject: [PATCH] [Doc]Fixed some spelling errors (#199) Signed-off-by: princepride --- docs/design/vllm_omni_design.md | 6 +++--- docs/getting_started/installation/README.md | 2 +- docs/usage/faq.md | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/design/vllm_omni_design.md b/docs/design/vllm_omni_design.md index eeb78997b..95ce146f3 100644 --- a/docs/design/vllm_omni_design.md +++ b/docs/design/vllm_omni_design.md @@ -16,7 +16,7 @@ vLLM-Omni is a multi-modality extension for vLLM that supports non-autoregressiv API Server --> OmniLLM/AsyncOmni (New, including multi engines) --> LLMEngine/AsyncLLM --> Engine Core --> Scheduler (New one for DiT) --> Executor (New one for diffusers) --> Worker (New one for DiT) - --> ModelRunner (New one for AR hiddenstate, New one for DiT) --> RequestState --> OutputProcessoer (New one for final multimodal output) + --> ModelRunner (New one for AR hiddenstate, New one for DiT) --> RequestState --> OutputProcessor (New one for final multimodal output) ## Core Components (Ordered by Data Flow) @@ -137,7 +137,7 @@ class OmniLLM(LLM): prompt_str, engine_request, tokenization_kwargs = self._process_stage_inputs(stage_config, **stage_args) # Add inputs to Engine - stage_engine.add_request(requesy_id, prompt_str, tokenization_kwargs) + stage_engine.add_request(request_id, prompt_str, tokenization_kwargs) # Run Engine stage_output = stage_engine.step() @@ -157,7 +157,7 @@ class OmniLLM(LLM): return self._process_ar_inputs(**stage_args) elif stage_config.engine_type == "DiT": return self._process_dit_inputs(**stage_args) - else + else: raise NotImplementedError def _process_dit_inputs(**stage_args)-> Any: diff --git a/docs/getting_started/installation/README.md b/docs/getting_started/installation/README.md index 7303bebbc..5abd9728b 100644 --- a/docs/getting_started/installation/README.md +++ b/docs/getting_started/installation/README.md @@ -1,6 +1,6 @@ # Installation -vLLM supports the following hardware platforms: +vLLM-Omni supports the following hardware platforms: - [GPU](gpu.md) - [NVIDIA CUDA](gpu.md) diff --git a/docs/usage/faq.md b/docs/usage/faq.md index bff520b77..53bf7c9fb 100644 --- a/docs/usage/faq.md +++ b/docs/usage/faq.md @@ -2,7 +2,7 @@ > Q: How many chips do I need to infer a model in vLLM-Omni? -A: Now, we support natively disaggregated deployment for different model stages within a model. There is a restriction that one chip can only has one AutoRegressive model stage. This is because the unified KV cache management of vLLM. Stages of other types can coexist with in a chip. The restriction will be resolved in later version. +A: Now, we support natively disaggregated deployment for different model stages within a model. There is a restriction that one chip can only have one AutoRegressive model stage. This is because the unified KV cache management of vLLM. Stages of other types can coexist within a chip. The restriction will be resolved in later version. > Q: When trying to run examples, I encounter error about backend of librosa or soundfile. How to solve it? @@ -14,7 +14,7 @@ sudo apt install ffmpeg > Q: I encounter some bugs or CI problems, which is urgent. How can I solve it? -A: At first, you can check current [issues](https://github.com/vllm-project/vllm-omni/issues) to find possible solutions. If non of these satisfy your demand and it is urgent, please find these [volunteers](https://docs.vllm.ai/projects/vllm-omni/en/latest/community/volunteers/) for help. +A: At first, you can check current [issues](https://github.com/vllm-project/vllm-omni/issues) to find possible solutions. If none of these satisfy your demand and it is urgent, please find these [volunteers](https://docs.vllm.ai/projects/vllm-omni/en/latest/community/volunteers/) for help. > Q: Does vLLM-Omni support AWQ or any other quantization?