|
liblloyal 1.0.0
Branched Inference for llama.cpp
|
Vacancy manager for seq_ids — the scarce KV cache resource. More...
Namespaces | |
| namespace | lloyal::kv::tenancy |
Variables | |
| constexpr llama_seq_id | lloyal::kv::NO_LEASE = static_cast<llama_seq_id>(-1) |
| Sentinel value indicating a branch has no KV residency. | |
Vacancy manager for seq_ids — the scarce KV cache resource.
A llama context has a fixed pool of seq_ids (typically 1–256). Each seq_id represents an independent recurrent state in the KV cache. Tenancy tracks which sequences are leased (owned by a branch) and which are vacant (available for allocation), providing symmetric acquire/release lifecycle.
|
constexpr |
Sentinel value indicating a branch has no KV residency.
-1 is chosen because 0 is a valid seq_id. Used as the default seq_id on freshly allocated (but not yet leased) branch slots.