diff --git a/.markdownlint.yaml b/.markdownlint.yaml index d0d317976..937487f47 100644 --- a/.markdownlint.yaml +++ b/.markdownlint.yaml @@ -6,9 +6,6 @@ MD024: MD031: list_items: false MD033: false -MD045: false MD046: false -MD051: false MD052: false -MD053: false MD059: false diff --git a/docs/contributing/benchmarks.md b/docs/contributing/benchmarks.md index dca01eab5..ec0dfc419 100644 --- a/docs/contributing/benchmarks.md +++ b/docs/contributing/benchmarks.md @@ -10,8 +10,6 @@ vLLM provides comprehensive benchmarking tools for performance testing and evalu - **[Parameter sweeps](#parameter-sweeps)**: Automate `vllm bench` runs for multiple configurations - **[Performance benchmarks](#performance-benchmarks)**: Automated CI benchmarks for development -[Benchmark CLI]: #benchmark-cli - ## Benchmark CLI This section guides you through running benchmark tests with the extensive diff --git a/docs/contributing/ci/update_pytorch_version.md b/docs/contributing/ci/update_pytorch_version.md index f983c25f2..09fd85a46 100644 --- a/docs/contributing/ci/update_pytorch_version.md +++ b/docs/contributing/ci/update_pytorch_version.md @@ -95,7 +95,7 @@ when manually triggering a build on Buildkite. This branch accomplishes two thin to warm it up so that future builds are faster.

- + Buildkite new build popup

## Update dependencies diff --git a/docs/deployment/frameworks/chatbox.md b/docs/deployment/frameworks/chatbox.md index 002935da5..5f7cef1a8 100644 --- a/docs/deployment/frameworks/chatbox.md +++ b/docs/deployment/frameworks/chatbox.md @@ -29,8 +29,8 @@ pip install vllm - API Path: `/chat/completions` - Model: `qwen/Qwen1.5-0.5B-Chat` - ![](../../assets/deployment/chatbox-settings.png) + ![Chatbox settings screen](../../assets/deployment/chatbox-settings.png) 1. Go to `Just chat`, and start to chat: - ![](../../assets/deployment/chatbox-chat.png) + ![Chatbot chat screen](../../assets/deployment/chatbox-chat.png) diff --git a/docs/deployment/frameworks/dify.md b/docs/deployment/frameworks/dify.md index 820ef0cbe..673cbf4b6 100644 --- a/docs/deployment/frameworks/dify.md +++ b/docs/deployment/frameworks/dify.md @@ -46,12 +46,12 @@ And install [Docker](https://docs.docker.com/engine/install/) and [Docker Compos - **Model Name for API Endpoint**: `Qwen/Qwen1.5-7B-Chat` - **Completion Mode**: `Completion` - ![](../../assets/deployment/dify-settings.png) + ![Dify settings screen](../../assets/deployment/dify-settings.png) 1. To create a test chatbot, go to `Studio → Chatbot → Create from Blank`, then select Chatbot as the type: - ![](../../assets/deployment/dify-create-chatbot.png) + ![Dify create chatbot screen](../../assets/deployment/dify-create-chatbot.png) 1. Click the chatbot you just created to open the chat interface and start interacting with the model: - ![](../../assets/deployment/dify-chat.png) + ![Dify chat screen](../../assets/deployment/dify-chat.png) diff --git a/docs/design/fused_moe_modular_kernel.md b/docs/design/fused_moe_modular_kernel.md index 76df0d8d8..e1a96be6c 100644 --- a/docs/design/fused_moe_modular_kernel.md +++ b/docs/design/fused_moe_modular_kernel.md @@ -19,9 +19,9 @@ The input activation format completely depends on the All2All Dispatch being use The FusedMoE operation is generally made of multiple operations, in both the Contiguous and Batched variants, as described in the diagrams below -![](../assets/design/fused_moe_modular_kernel/fused_moe_non_batched.png "FusedMoE Non-Batched") +![FusedMoE Non-Batched](../assets/design/fused_moe_modular_kernel/fused_moe_non_batched.png) -![](../assets/design/fused_moe_modular_kernel/fused_moe_batched.png "FusedMoE Batched") +![FusedMoE Batched](../assets/design/fused_moe_modular_kernel/fused_moe_batched.png) !!! note The main difference, in terms of operations, between the Batched and Non-Batched cases is the Permute / Unpermute operations. All other operations remain. @@ -57,7 +57,7 @@ The `FusedMoEModularKernel` acts as a bridge between the `FusedMoEPermuteExperts The `FusedMoEPrepareAndFinalize` abstract class exposes `prepare`, `prepare_no_receive` and `finalize` functions. The `prepare` function is responsible for input activation Quantization and All2All Dispatch. If implemented, The `prepare_no_receive` is like `prepare` except it does not wait to receive results from other workers. Instead it returns a "receiver" callback that must be invoked to wait for the final results of worker. It is not required that this method is supported by all `FusedMoEPrepareAndFinalize` classes, but if it is available, it can be used to interleave work with the initial all to all communication, e.g. interleaving shared experts with fused experts. The `finalize` function is responsible for invoking the All2All Combine. Additionally the `finalize` function may or may not do the TopK weight application and reduction (Please refer to the TopKWeightAndReduce section) -![](../assets/design/fused_moe_modular_kernel/prepare_and_finalize_blocks.png "FusedMoEPrepareAndFinalize Blocks") +![FusedMoEPrepareAndFinalize Blocks](../assets/design/fused_moe_modular_kernel/prepare_and_finalize_blocks.png) ### FusedMoEPermuteExpertsUnpermute @@ -88,7 +88,7 @@ The core FusedMoE implementation performs a series of operations. It would be in It is sometimes efficient to perform TopK weight application and Reduction inside the `FusedMoEPermuteExpertsUnpermute::apply()`. Find an example [here](https://github.com/vllm-project/vllm/pull/20228). We have a `TopKWeightAndReduce` abstract class to facilitate such implementations. Please refer to the TopKWeightAndReduce section. `FusedMoEPermuteExpertsUnpermute::finalize_weight_and_reduce_impl()` returns the `TopKWeightAndReduce` object that the implementation wants the `FusedMoEPrepareAndFinalize::finalize()` to use. -![](../assets/design/fused_moe_modular_kernel/fused_experts_blocks.png "FusedMoEPermuteExpertsUnpermute Blocks") +![FusedMoEPermuteExpertsUnpermute Blocks](../assets/design/fused_moe_modular_kernel/fused_experts_blocks.png) ### FusedMoEModularKernel