29 const std::vector<continuum::Value>& inputs,
30 const std::optional<BackendState>& prefix_state,
31 std::int32_t remaining_tokens)
override;
Definition backend.hpp:36
Definition mlx_backend.hpp:21
BackendRunResult run_with_cache(const ir::Node &node, const std::vector< continuum::Value > &inputs, const std::optional< BackendState > &prefix_state, std::int32_t remaining_tokens) override
std::string tensor_backend_type() const override
Definition mlx_backend.hpp:24
BackendCapabilities capabilities() const override
static std::string runtime()
"mlx <version> (gpu|cpu)" when built against MLX, else "reference (built without MLX)".
Definition anthropic.hpp:4
Definition backend.hpp:30
Definition backend.hpp:20