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

speculative : add tree-based sampling example (#3624)

Browse source 
* sampling : one sequence per sampling context

ggml-ci

* speculative : add tree-based sampling support

ggml-ci

* speculative : reuse the n_parallel CLI param

* speculative : refactor sampling

* examples : fix build after sampling refactoring

ggml-ci

* batched : fix n_seq_id

* sampling : fix malloc

ggml-ci

* swift : fix build

ggml-ci

* swift : try to fix build

ggml-ci

* prompts : add assistant.txt

* common : add llama_batch_add() and llama_batch_clear() helpers

* speculative : minor refactor

ggml-ci

* minor : comments + rename

ggml-ci

* speculative : fix off-by-one for n_drafted

* speculative : fix the n_drafted fix + p constants
This commit is contained in:
Georgi Gerganov 2023-10-18 16:21:57 +03:00 • committed by GitHub
parent c67fe68e41
commit 0e89203b51
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
21 changed files with 737 additions and 578 deletions
Download patch file Download diff file Expand all files Collapse all files

21
common/common.cpp
View file

@ -820,6 +820,27 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
return cparams;
}
void llama_batch_clear(struct llama_batch & batch) {
batch.n_tokens = 0;
}
void llama_batch_add(
struct llama_batch & batch,
llama_token id,
llama_pos pos,
const std::vector<llama_seq_id> & seq_ids,
bool logits) {
batch.token [batch.n_tokens] = id;
batch.pos [batch.n_tokens] = pos,
batch.n_seq_id[batch.n_tokens] = seq_ids.size();
for (size_t i = 0; i < seq_ids.size(); ++i) {
batch.seq_id[batch.n_tokens][i] = seq_ids[i];
}
batch.logits [batch.n_tokens] = logits;
batch.n_tokens++;
}
std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_params(gpt_params & params) {
auto mparams = llama_model_params_from_gpt_params(params);