mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-19 09:15:04 +02:00
swift : fix build
ggml-ci
This commit is contained in:
@@ -69,7 +69,7 @@ for id: llama_token in tokens {
|
||||
|
||||
print("\n")
|
||||
|
||||
var batch = llama_batch_init(max(Int32(tokens.count), Int32(n_parallel)), 0)
|
||||
var batch = llama_batch_init(max(Int32(tokens.count), Int32(n_parallel)), 0, 1)
|
||||
defer {
|
||||
llama_batch_free(batch)
|
||||
}
|
||||
@@ -80,7 +80,8 @@ batch.n_tokens = Int32(tokens.count)
|
||||
for (i, token) in tokens.enumerated() {
|
||||
batch.token[i] = token
|
||||
batch.pos[i] = Int32(i)
|
||||
batch.seq_id[i] = 0
|
||||
batch.n_seq_id[i] = 1
|
||||
batch.seq_id[i][0] = 0
|
||||
batch.logits[i] = 0
|
||||
}
|
||||
|
||||
@@ -169,7 +170,8 @@ while n_cur <= n_len {
|
||||
// push this new token for next evaluation
|
||||
batch.token[Int(batch.n_tokens)] = new_token_id
|
||||
batch.pos[Int(batch.n_tokens)] = n_cur
|
||||
batch.seq_id[Int(batch.n_tokens)] = Int32(i)
|
||||
batch.n_seq_id[Int(batch.n_tokens)] = 1
|
||||
batch.seq_id[Int(batch.n_tokens)][0] = Int32(i)
|
||||
batch.logits[Int(batch.n_tokens)] = 1
|
||||
|
||||
i_batch[i] = batch.n_tokens
|
||||
|
||||
Reference in New Issue
Block a user