Initial ForgeLM import

crates/inference-core/src/profile.rs

@@ -0,0 +1,59 @@
+/// Predefined runtime profiles matching the plan targets.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum RuntimeProfile {
+    /// Qwen3.5-4B – maximum TPS, text-only, flash attention, moderate context.
+    Turbo4B,
+    /// Qwen3.5-9B – balanced quality/speed, tuned KV cache.
+    Balanced9B,
+    /// CPU-only fallback for machines without a GPU.
+    CpuFallback,
+}
+
+impl RuntimeProfile {
+    /// Returns sensible defaults for each profile.
+    pub fn defaults(&self) -> ProfileDefaults {
+        match self {
+            Self::Turbo4B => ProfileDefaults {
+                n_gpu_layers: 999,
+                n_ctx: 4096,
+                n_batch: 512,
+                n_ubatch: 128,
+                flash_attn: true,
+                n_threads: 8,
+            },
+            Self::Balanced9B => ProfileDefaults {
+                n_gpu_layers: 999,
+                n_ctx: 2048,
+                n_batch: 256,
+                n_ubatch: 64,
+                flash_attn: true,
+                n_threads: 8,
+            },
+            Self::CpuFallback => ProfileDefaults {
+                n_gpu_layers: 0,
+                n_ctx: 2048,
+                n_batch: 128,
+                n_ubatch: 32,
+                flash_attn: false,
+                n_threads: num_cpus(),
+            },
+        }
+    }
+}
+
+fn num_cpus() -> i32 {
+    // Simple fallback; replace with `num_cpus` crate if needed.
+    std::thread::available_parallelism()
+        .map(|n| n.get() as i32)
+        .unwrap_or(4)
+}
+
+#[derive(Debug, Clone)]
+pub struct ProfileDefaults {
+    pub n_gpu_layers: i32,
+    pub n_ctx: u32,
+    pub n_batch: u32,
+    pub n_ubatch: u32,
+    pub flash_attn: bool,
+    pub n_threads: i32,
+}