ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH (llama/18535)

ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH (llama/18535)

* ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
* makes the min_batch_size for triggering op offload configurable via env var, defaulting to the prior hardcoded value of 32

* ggml: read GGML_OP_OFFLOAD_MIN_BATCH once and store to dev ctx

* cann: forward declaration of device context struct

* cann: move offload op check after device context declaration

* cuda: fix whitespace

Co-authored-by: Aman Gupta <redacted>
---------

Co-authored-by: Aman Gupta <redacted>