API ReferenceAndroid
Enums and Constants
Android enum and support types for ZeticMLange.
This page reflects ZeticMLange Android 1.9.0.
General Model Types
| Type | Values |
|---|---|
ModelMode | RUN_AUTO, RUN_FP32, RUN_QUANTIZED, RUN_SPEED, RUN_ACCURACY |
QuantType | FP32, FP16, INT |
APType | CPU, GPU, NPU, NA |
ModelCacheHandlingPolicy | REMOVE_OVERLAPPING, KEEP_EXISTING |
Target contains backend identifiers used by selected general-model artifacts. Most apps use ModelMode and let backend selection choose the target.
LLM Types
| Type | Values |
|---|---|
LLMModelMode | RUN_AUTO, RUN_SPEED, RUN_ACCURACY |
LLMTarget | LLAMA_CPP, LITERT_LM, MLLM |
LLMQuantType | GGUF_QUANT_ORG, GGUF_QUANT_F16, GGUF_QUANT_BF16, GGUF_QUANT_Q8_0, GGUF_QUANT_Q4_K_M, GGUF_QUANT_Q3_K_M, GGUF_QUANT_Q2_K, GGUF_QUANT_Q6_K |
LLMKVCacheCleanupPolicy | CLEAN_UP_ON_FULL, DO_NOT_CLEAN_UP |
KVStateStatus | Status values returned by KV state persistence operations. |
LLMInitOption
data class LLMInitOption(
val kvCacheCleanupPolicy: LLMKVCacheCleanupPolicy = LLMKVCacheCleanupPolicy.CLEAN_UP_ON_FULL,
val nCtx: Int = 2048,
)| Field | Default | Description |
|---|---|---|
kvCacheCleanupPolicy | CLEAN_UP_ON_FULL | In-memory KV-cache behavior when context storage is full. |
nCtx | 2048 | Requested context size. The runtime may normalize it. |
Result Types
| Type | Purpose |
|---|---|
LLMRunResult | Result from starting LLM generation. Includes status and prompt token count. |
LLMNextTokenResult | Token result returned by waitForNextToken(). |
AllowedRunConfig | Describes available local LFM-VL run configurations. Not exposed in website examples. |