diff --git a/docs/source/index.md b/docs/source/index.md index 3842b1e..fafeb40 100644 --- a/docs/source/index.md +++ b/docs/source/index.md @@ -43,16 +43,10 @@ faqs :::{toctree} :caption: User Guide :maxdepth: 1 -user_guide/suppoted_features -user_guide/supported_models -user_guide/env_vars -user_guide/additional_config -user_guide/sleep_mode -user_guide/graph_mode.md -user_guide/lora.md -user_guide/quantization.md +user_guide/support_matrix/index +user_guide/configuration/index +user_guide/feature_guide/index user_guide/release_notes -user_guide/structured_output ::: % How to contribute to the vLLM Ascend project diff --git a/docs/source/tutorials/multi_node.md b/docs/source/tutorials/multi_node.md index 64475c3..865cc40 100644 --- a/docs/source/tutorials/multi_node.md +++ b/docs/source/tutorials/multi_node.md @@ -54,7 +54,7 @@ hccn_tool -i 0 -ping -g address 10.20.0.20 ``` ## Run with docker -Assume you have two Altas 800 A2(64G*8) nodes, and want to deploy the `deepseek-v3-w8a8` quantitative model across multi-node. +Assume you have two Atlas 800 A2(64G*8) nodes, and want to deploy the `deepseek-v3-w8a8` quantitative model across multi-node. ```shell # Define the image and container name diff --git a/docs/source/user_guide/additional_config.md b/docs/source/user_guide/configuration/additional_config.md similarity index 100% rename from docs/source/user_guide/additional_config.md rename to docs/source/user_guide/configuration/additional_config.md diff --git a/docs/source/user_guide/env_vars.md b/docs/source/user_guide/configuration/env_vars.md similarity index 79% rename from docs/source/user_guide/env_vars.md rename to docs/source/user_guide/configuration/env_vars.md index 20304ac..ff4af76 100644 --- a/docs/source/user_guide/env_vars.md +++ b/docs/source/user_guide/configuration/env_vars.md @@ -2,7 +2,7 @@ vllm-ascend uses the following environment variables to configure the system: -:::{literalinclude} ../../../vllm_ascend/envs.py +:::{literalinclude} ../../../../vllm_ascend/envs.py :language: python :start-after: begin-env-vars-definition :end-before: end-env-vars-definition diff --git a/docs/source/user_guide/configuration/index.md b/docs/source/user_guide/configuration/index.md new file mode 100644 index 0000000..3783683 --- /dev/null +++ b/docs/source/user_guide/configuration/index.md @@ -0,0 +1,10 @@ +# Configuration Guide + +This section provides a detailed configuration guide of vLLM Ascend. + +:::{toctree} +:caption: Configuration Guide +:maxdepth: 1 +env_vars +additional_config +::: diff --git a/docs/source/user_guide/graph_mode.md b/docs/source/user_guide/feature_guide/graph_mode.md similarity index 96% rename from docs/source/user_guide/graph_mode.md rename to docs/source/user_guide/feature_guide/graph_mode.md index 77e91dd..d7f574b 100644 --- a/docs/source/user_guide/graph_mode.md +++ b/docs/source/user_guide/feature_guide/graph_mode.md @@ -59,7 +59,7 @@ online example: vllm serve Qwen/Qwen2-7B-Instruct --additional-config='{"torchair_graph_config": {"enabled": true},"ascend_scheduler_config": {"enabled": true,}}' ``` -You can find more detail about additional config [here](./additional_config.md) +You can find more detail about additional config [here](../configuration/additional_config.md). ## Fallback to Eager Mode diff --git a/docs/source/user_guide/images/structured_output_1.png b/docs/source/user_guide/feature_guide/images/structured_output_1.png similarity index 100% rename from docs/source/user_guide/images/structured_output_1.png rename to docs/source/user_guide/feature_guide/images/structured_output_1.png diff --git a/docs/source/user_guide/feature_guide/index.md b/docs/source/user_guide/feature_guide/index.md new file mode 100644 index 0000000..c24faac --- /dev/null +++ b/docs/source/user_guide/feature_guide/index.md @@ -0,0 +1,13 @@ +# Feature Guide + +This section provides a detailed usage guide of vLLM Ascend features. + +:::{toctree} +:caption: Feature Guide +:maxdepth: 1 +graph_mode +quantization +sleep_mode +structured_output +lora +::: diff --git a/docs/source/user_guide/lora.md b/docs/source/user_guide/feature_guide/lora.md similarity index 96% rename from docs/source/user_guide/lora.md rename to docs/source/user_guide/feature_guide/lora.md index 40cdf46..1529b6e 100644 --- a/docs/source/user_guide/lora.md +++ b/docs/source/user_guide/feature_guide/lora.md @@ -1,4 +1,4 @@ -# LoRA Adapters +# LoRA Adapters Guide Like vLLM, vllm-ascend supports LoRA as well. The usage and more details can be found in [vLLM official document](https://docs.vllm.ai/en/latest/features/lora.html). diff --git a/docs/source/user_guide/quantization.md b/docs/source/user_guide/feature_guide/quantization.md similarity index 100% rename from docs/source/user_guide/quantization.md rename to docs/source/user_guide/feature_guide/quantization.md diff --git a/docs/source/user_guide/sleep_mode.md b/docs/source/user_guide/feature_guide/sleep_mode.md similarity index 99% rename from docs/source/user_guide/sleep_mode.md rename to docs/source/user_guide/feature_guide/sleep_mode.md index c36b96b..8fef30a 100644 --- a/docs/source/user_guide/sleep_mode.md +++ b/docs/source/user_guide/feature_guide/sleep_mode.md @@ -1,4 +1,4 @@ -# Sleep Mode +# Sleep Mode Guide ## Overview diff --git a/docs/source/user_guide/structured_output.md b/docs/source/user_guide/feature_guide/structured_output.md similarity index 100% rename from docs/source/user_guide/structured_output.md rename to docs/source/user_guide/feature_guide/structured_output.md diff --git a/docs/source/user_guide/release.template.md b/docs/source/user_guide/release.template.md deleted file mode 100644 index dec857a..0000000 --- a/docs/source/user_guide/release.template.md +++ /dev/null @@ -1,13 +0,0 @@ -## {version} -### Highlights -- {feature} -### Bug fixes -- {bug} -### Other changes -- {change} -### Known issues -- {issue} -### Upgrade Notes -- {upgrade} -### Deprecation Notes -- {deprecation} diff --git a/docs/source/user_guide/support_matrix/index.md b/docs/source/user_guide/support_matrix/index.md new file mode 100644 index 0000000..3a8bf68 --- /dev/null +++ b/docs/source/user_guide/support_matrix/index.md @@ -0,0 +1,10 @@ +# Features and models + +This section provides a detailed supported matrix by vLLM Ascend. + +:::{toctree} +:caption: Support Matrix +:maxdepth: 1 +supported_models +supported_features +::: diff --git a/docs/source/user_guide/suppoted_features.md b/docs/source/user_guide/support_matrix/supported_features.md similarity index 100% rename from docs/source/user_guide/suppoted_features.md rename to docs/source/user_guide/support_matrix/supported_features.md diff --git a/docs/source/user_guide/supported_models.md b/docs/source/user_guide/support_matrix/supported_models.md similarity index 98% rename from docs/source/user_guide/supported_models.md rename to docs/source/user_guide/support_matrix/supported_models.md index ef24ba4..331e028 100644 --- a/docs/source/user_guide/supported_models.md +++ b/docs/source/user_guide/support_matrix/supported_models.md @@ -1,4 +1,4 @@ -# Supported Models +# Model Support ## Text-only Language Models