support Deepseek3.2

[sufubao]

[gemini-code-assist[bot]]

Summary of Changes

Hello @sufubao, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates the Deepseek3.2 model into the system, extending the existing Deepseek2 framework. The changes involve significant architectural additions to support Deepseek3.2's distinct attention mechanism and FP8 quantization, ensuring efficient inference. This includes new data structures for managing attention states, specialized memory allocation, and highly optimized Triton kernels for core computational tasks.

Highlights

• Deepseek3.2 Model Support: Introduced comprehensive support for the Deepseek3.2 model, including new inference structures, specialized memory management, and custom Triton kernels tailored for its unique attention mechanism and FP8 quantization.
• Non-Standard Attention (NSA) Indexing: Implemented a dedicated NSA Indexer (NSAIndexerInfer) and associated structures (Deepseek3_2FlashAttentionStateInfo, NSAIndexerWeight) to manage and compute indices for Deepseek3.2's attention mechanism, which involves dynamic top-k selection.
• Custom Memory Management: Added Deepseek3_2MemoryManager and Deepseek3_2FP8KVMemoryManager to handle the specific memory requirements of Deepseek3.2, including a sub-memory manager for indexer KV data. The base MemoryManager was updated to support sub-managers.
• New Triton Kernels for Optimization: Developed several new Triton kernels: act_quant for block-wise FP8 activation quantization, destindex_copy_indexer_ks and extract_indexer_ks for efficient handling of indexer KV data, and fp8_paged_mqa_logits for optimized FP8 Multi-Query Attention logits computation.
• Refined Weight Loading and Verification: Enhanced the TransformerLayerWeight class to recursively load and verify nested transformer layer weights, ensuring proper initialization for complex model architectures like Deepseek3.2.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.