chore: stabilize current head before Phase 10a QC
This commit is contained in:
@@ -172,8 +172,8 @@ impl LlmEngine {
|
||||
// follow-up in docs/superpowers/specs/2026-05-09-battery-gpu-aware-
|
||||
// thread-tuning-design.md (§ Out of scope).
|
||||
let gpu_offloaded = use_gpu && gpu_layers >= model.n_layer();
|
||||
let thread_count = i32::try_from(inference_thread_count(Workload::Llm, gpu_offloaded))
|
||||
.unwrap_or(4);
|
||||
let thread_count =
|
||||
i32::try_from(inference_thread_count(Workload::Llm, gpu_offloaded)).unwrap_or(4);
|
||||
let ctx_params = LlamaContextParams::default()
|
||||
.with_n_ctx(Some(
|
||||
NonZeroU32::new(n_ctx).expect("n_ctx must be non-zero"),
|
||||
|
||||
Reference in New Issue
Block a user