Internvl3 Request Processing

class InternVL3RequestProcessing : public trt_edgellm::safety::SafetyRequestProcessing

Public Functions

InternVL3RequestProcessing(

std::unique_ptr<TokenizerCapability> tokenizer,

std::unique_ptr<MultimodalPreprocessorCapability> preprocessor,

std::unique_ptr<EmbeddingCapability> embedding,

std::unique_ptr<SamplerCapability> sampler

) noexcept

virtual SafetyStatus configure(

SafetyRuntimeArtifactBundle const &artifacts,

nlohmann::json const &llmConfig,

nlohmann::json const &visualConfig

) noexcept override

Load tokenizer/template/embedding configuration and validate artifact compatibility before allocation.

virtual ProcessingConfiguration const &configuration(

) const noexcept override

virtual ProcessingCapabilitySet capabilities() noexcept override

virtual SafetyStatus prepareRequest(

LLMGenerationRequest const &request,

ProcessingRequest &prepared

) noexcept override

Validate all requested features before SDK work; write into prepared, bounded input storage. The returned views remain valid until the next request.

virtual SafetyStatus validateResponse(

LLMGenerationRequest const &request,

LLMGenerationResponse const &response

) const noexcept override

Validate caller-owned output capacities before any request execution.

virtual SafetyStatus formatResponse(

ModelInferenceResult const &result,

LLMGenerationResponse &response

) noexcept override

Decode text into caller-prepared storage without allocation. Called only after successful generation.