vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
#	ci/run.sh
#	ggml-quants.c
#	ggml.c
#	grammars/json.gbnf
#	grammars/json_arr.gbnf
#	llama.cpp
#	scripts/compare-llama-bench.py
This commit is contained in:
Concedo 2024-03-09 10:58:49 +08:00
commit b4ca54401d
36 changed files with 49217 additions and 49887 deletions
Download patch file Download diff file Expand all files Collapse all files

20
examples/parallel/parallel.cpp
View file

@ -109,6 +109,9 @@ int main(int argc, char ** argv) {
// number of simultaneous "clients" to simulate
const int32_t n_clients = params.n_parallel;
// dedicate one sequence to the system prompt
params.n_parallel += 1;
// requests to simulate
const int32_t n_seq = params.n_sequences;
@ -198,8 +201,8 @@ int main(int argc, char ** argv) {
}
// assign the system KV cache to all parallel sequences
for (int32_t i = 1; i < n_clients; ++i) {
llama_kv_cache_seq_cp(ctx, 0, i, 0, n_tokens_system);
for (int32_t i = 1; i <= n_clients; ++i) {
llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
}
LOG_TEE("\n");
@ -223,15 +226,17 @@ int main(int argc, char ** argv) {
client.i_batch = batch.n_tokens;
llama_batch_add(batch, client.sampled, n_tokens_system + client.n_prompt + client.n_decoded, { client.id }, true);
llama_batch_add(batch, client.sampled, n_tokens_system + client.n_prompt + client.n_decoded, { client.id + 1 }, true);
client.n_decoded += 1;
}
if (batch.n_tokens == 0) {
// all sequences have ended - clear the entire KV cache
for (int i = 0; i < n_clients; ++i) {
llama_kv_cache_seq_rm(ctx, i, n_tokens_system, -1);
for (int i = 1; i <= n_clients; ++i) {
llama_kv_cache_seq_rm(ctx, i, -1, -1);
// but keep the system prompt
llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
}
LOG_TEE("%s: clearing the KV cache\n", __func__);
@ -257,7 +262,7 @@ int main(int argc, char ** argv) {
tokens_prompt = ::llama_tokenize(ctx, client.prompt, false);
for (size_t i = 0; i < tokens_prompt.size(); ++i) {
llama_batch_add(batch, tokens_prompt[i], i + n_tokens_system, { client.id }, false);
llama_batch_add(batch, tokens_prompt[i], i + n_tokens_system, { client.id + 1 }, false);
}
// extract the logits only for the last token
@ -368,7 +373,8 @@ int main(int argc, char ** argv) {
}
// delete only the generated part of the sequence, i.e. keep the system prompt in the cache
llama_kv_cache_seq_rm(ctx, client.id, n_tokens_system, -1);
llama_kv_cache_seq_rm(ctx, client.id + 1, -1, -1);
llama_kv_cache_seq_cp(ctx, 0, client.id + 1, -1, -1);
const auto t_main_end = ggml_time_us();