refactor: simplify inference engine and backend dispatch

- merge _generate_streaming/_generate_non_streaming into single _generate() with stream flag
- delete dead GenerationRequest class and generate_with_request method
- inline _next_token helper into generate_async
- replace flash-attn double-checked locking with functools.lru_cache
- extract _write_and_gather_kv helper shared by TorchNative/FlashAttn backends
- inline _kv_cache_is_contiguous into its sole call site in FlashAttnBackend
- change default backend priority from flash>cuda>torch to cuda>flash>torch
- add ASTR_BACKEND env var to override default backend at resolve time
- add supports_graph() static method to AttentionBackend ABC, override in CudaBackend
- replace isinstance(get_backend(), CudaBackend) with get_backend().supports_graph() in executor
- add torch.cuda.is_available() guard to CudaBackend.supports()

astrai/__init__.py

@@ -21,7 +21,6 @@ from astrai.dataset import (
 )
 from astrai.factory import BaseFactory
 from astrai.inference import (
-    GenerationRequest,
     InferenceEngine,
     ProtocolHandler,
     SamplingPipeline,
@@ -98,7 +97,6 @@ __all__ = [
     "EmbeddingEncoder",
     "EncoderConfig",
     "ExecutorFactory",
-    "GenerationRequest",
     "InferenceEngine",
     "LoRAConfig",
     "Pipeline",