feat: first cut at actual token generation and model loading

native/metal/ds4_ssd.h

@@ -0,0 +1,36 @@
+#ifndef DS4_SSD_H
+#define DS4_SSD_H
+
+#include <stdbool.h>
+#include <stdint.h>
+
+typedef struct {
+    void *ptr;
+    uint64_t bytes;
+} ds4_ssd_memory_lock;
+
+typedef struct {
+    uint64_t model_target_bytes;
+    uint64_t cache_bytes;
+    uint64_t effective_cache_bytes;
+    uint32_t cache_experts;
+} ds4_ssd_cache_plan;
+
+bool ds4_parse_gib_arg(const char *s, uint64_t *bytes);
+bool ds4_parse_streaming_cache_experts_arg(const char *s,
+                                           uint32_t   *experts,
+                                           uint64_t   *bytes);
+
+uint32_t ds4_ssd_cache_experts_for_byte_budget(uint64_t bytes,
+                                               uint64_t per_expert_bytes);
+bool ds4_ssd_auto_cache_plan(uint64_t            recommended_bytes,
+                             uint64_t            non_routed_bytes,
+                             uint64_t            per_expert_bytes,
+                             uint64_t            max_model_experts,
+                             ds4_ssd_cache_plan *out);
+
+bool ds4_ssd_memory_lock_acquire(ds4_ssd_memory_lock *lock,
+                                 uint64_t             bytes);
+void ds4_ssd_memory_lock_release(ds4_ssd_memory_lock *lock);
+
+#endif