vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '32c8486e1f' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/nix/package.nix
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	README.md
#	build.zig
#	llama.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-04-07 20:39:17 +08:00
commit 22f543d09b
32 changed files with 3521 additions and 1792 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/server/server.cpp
View file

@ -100,6 +100,7 @@ struct slot_params {
uint32_t seed = -1; // RNG seed
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_discard = 0; // number of tokens after n_keep that may be discarded when shifting context, 0 defaults to half
int32_t n_predict = -1; // new tokens to predict
std::vector<std::string> antiprompt;
@ -747,7 +748,8 @@ struct server_context {
{
const int32_t n_batch = llama_n_batch(ctx);
batch = llama_batch_init(n_batch, 0, params.n_parallel);
// only a single seq_id per token is needed
batch = llama_batch_init(n_batch, 0, 1);
}
metrics.init();
@ -847,6 +849,7 @@ struct server_context {
slot.sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta);
slot.sparams.penalize_nl = json_value(data, "penalize_nl", default_sparams.penalize_nl);
slot.params.n_keep = json_value(data, "n_keep", slot.params.n_keep);
slot.params.n_discard = json_value(data, "n_discard", default_params.n_discard);
slot.params.seed = json_value(data, "seed", default_params.seed);
slot.sparams.n_probs = json_value(data, "n_probs", default_sparams.n_probs);
slot.sparams.min_keep = json_value(data, "min_keep", default_sparams.min_keep);
@ -1254,6 +1257,7 @@ struct server_context {
{"stop", slot.params.antiprompt},
{"n_predict", slot.params.n_predict}, // TODO: fix duplicate key n_predict
{"n_keep", slot.params.n_keep},
{"n_discard", slot.params.n_discard},
{"ignore_eos", ignore_eos},
{"stream", slot.params.stream},
{"logit_bias", slot.sparams.logit_bias},
@ -1697,7 +1701,7 @@ struct server_context {
// Shift context
const int n_keep = slot.params.n_keep + add_bos_token;
const int n_left = (int) system_tokens.size() + slot.n_past - n_keep;
const int n_discard = n_left / 2;
const int n_discard = slot.params.n_discard ? slot.params.n_discard : (n_left / 2);
LOG_INFO("slot context shift", {
{"id_slot", slot.id},