ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

perplexity : support using multiple sequences to allow larger batch sizes (#5946)

Browse source 
* perplexity : support using multiple sequences to allow larger batch sizes

ggml-ci

* set cparams.n_parallel to the number of sequences

* print tested n_ctx, add assert
This commit is contained in:
slaren 2024-03-09 19:55:54 +01:00 • committed by GitHub
parent 098dbaab44
commit d894f352bf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 107 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama.cpp
View file

@ -8925,17 +8925,29 @@ static int llama_decode_internal(
if (batch.logits) {
logits_out.resize(n_vocab * n_tokens);
int32_t i_first = -1;
for (uint32_t i = 0; i < n_tokens; i++) {
if (batch.logits[i] == 0) {
continue;
if (batch.logits[i] && i_first == -1) {
i_first = (int32_t) i;
}
if (batch.logits[i] == 0 || i == n_tokens - 1) {
if (i_first != -1) {
int i_last = batch.logits[i] == 0 ? i : i + 1;
// extract logits for the range [i_first, i_last)
// group the requests to minimize the number of calls to the backend
ggml_backend_tensor_get_async(backend_res, res,
logits_out.data() + (n_vocab*i_first),
(n_vocab*i_first)*sizeof(float),
(i_last - i_first)*n_vocab*sizeof(float));
i_first = -1;
}
}
ggml_backend_tensor_get_async(backend_res, res, logits_out.data() + (n_vocab*i), (n_vocab*i)*sizeof(float), n_vocab*sizeof(float));
#ifndef NDEBUG
logits_valid[i] = true;
logits_valid[i] = batch.logits[i] != 0;
#endif
}
} else if (lctx.logits_all) {
logits_out.resize(n_vocab * n_tokens);
logits_out.resize(n_vocab*n_tokens);
ggml_backend_tensor_get_async(backend_res, res, logits_out.data(), 0, n_vocab*n_tokens*sizeof(float));
#ifndef NDEBUG
std::fill(logits_valid.begin(), logits_valid.end(), true);