Adding rwkv_eval_array operation

[PicoCreator]

Adding a varient of rwkv_eval as rwkv_eval_array for array operations.

This is useful for X language bindings, where we can eval a larger context, without switching back and forth between X language and C lang context. (I am currently working on a nodejs binding)

Subsequently, if you do add support for "transformer" mode, this should use the "transformer" mode (i dun see the point to doing so though, for CPU eval)

[saharNooby]

I propose following implementation:

bool rwkv_eval_sequence(struct rwkv_context * ctx, int32_t * token_sequence, uint32_t n_tokens, float * state_in, float * state_out, float * logits_out) {
    RWKV_ASSERT_FALSE(n_tokens < 1, "Token count must be positive, got %d", n_tokens);

    for (uint32_t i = 0; i < n_tokens; i++) {
        if (!rwkv_eval(ctx, token_sequence[i], i == 0 ? state_in : state_out, state_out, logits_out)) {
            return false;
        }
    }

    return true;
}

• it looks simpler to me
• I would prefer to use term sequence instead of array
• token count made unsigned and with specific size (IDK what exactly int is in C and try to avoid it lol)
• added token count correctness check, so users don't try to process zero tokens

Function signature in rwkv.h should be changed accordingly.

[saharNooby]

Suggested change

//

[saharNooby]

Suggested change

	// Evaluates the model for multiple token in an array
	// Evaluates the model for a sequence of tokens.

[saharNooby]

Please add test case for this new function into tests/test_tiny_rwkv.c. Probably, void test_model(...) can be extended with a boolean arg whether to use regular eval or eval_sequence.

[saharNooby]

It would also be useful to add corresponding method to rwkv/rwkv_cpp_shared_library.py, but this is not a blocker for merge -- until we have really optimized sequence processing mode, overhead when calling C from Python side in a loop seems insignificant.

[LoganDark]

This is no longer necessary after #89