sampling : add support for backend sampling

This commit adds support for performing sampling operations on the
backend (e.g. GPU) as part of the model computation graph.

The motivation for this feature is to enable sampling to be performed
directly on the backend as part of the computation graph being executed,
allowing for some or all of the sampling to be done on the backend.

For example, the backend sampler chain might select/sample a token
directly in which case only the sampled token needs to be transferred
from device memory to host memory.

It is also possible for the backend samplers to perform filtering of
the logits, or compute and filter the probability distribution, in
which case only the filtered logits or probabilites need to be
transferred back to system memory for further processing by CPU
samplers.

Currently the backend sampling works in a similar manner to how
pooling works, it is a function that is called by build_graph and the
sampler operations become part of the models computation graph.

common/common.cpp

@@ -8,6 +8,7 @@
 #include "common.h"
 #include "log.h"
 #include "llama.h"
+#include "sampling.h"
 
 #include <algorithm>
 #include <cinttypes>
@@ -956,6 +957,8 @@ struct common_init_result common_init_from_params(common_params & params) {
     const llama_vocab * vocab = llama_model_get_vocab(model);
 
     auto cparams = common_context_params_to_llama(params);
+    cparams.samplers = params.backend_samplers;
+    cparams.n_samplers = params.n_backend_samplers;
 
     llama_context * lctx = llama_init_from_model(model, cparams);
     if (lctx == NULL) {