root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-09-22 21:16:20 +00:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

Merge 4af076b494 into a5b57b08ce

Browse Source
This commit is contained in:
Vinesh Janarthanan 2024-09-22 11:34:31 +02:00 committed by GitHub
commit 7fca5a04f3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 16 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@ -691,7 +691,7 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
[](gpt_params & params) {
params.ctx_shift = false;
}
).set_examples({LLAMA_EXAMPLE_MAIN}));
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}));
add_opt(llama_arg(
{"--chunks"}, "N",
format("max number of chunks to process (default: %d, -1 = all)", params.n_chunks),

1
examples/server/README.md
View File

@ -37,6 +37,7 @@ The project is under active development, and we are [looking for feedback and co
| `--poll-batch <0\|1>` | use polling to wait for work (default: same as --poll) |
| `-c, --ctx-size N` | size of the prompt context (default: 0, 0 = loaded from model)<br/>(env: LLAMA_ARG_CTX_SIZE) |
| `-n, --predict, --n-predict N` | number of tokens to predict (default: -1, -1 = infinity, -2 = until context filled)<br/>(env: LLAMA_ARG_N_PREDICT) |
| `--no-context-shift` | stop generation when context window is full (default: context shift is enabled)<br/> |
| `-b, --batch-size N` | logical maximum batch size (default: 2048)<br/>(env: LLAMA_ARG_BATCH) |
| `-ub, --ubatch-size N` | physical maximum batch size (default: 512)<br/>(env: LLAMA_ARG_UBATCH) |
| `--keep N` | number of tokens to keep from the initial prompt (default: 0, -1 = all) |

16
examples/server/server.cpp
View File

@ -1476,11 +1476,10 @@ struct server_context {
std::vector<server_task_result> results(id_tasks.size());
for (size_t i = 0; i < id_tasks.size(); i++) {
server_task_result result = queue_results.recv(id_tasks);
if (result.error) {
error_handler(result.data);
cancel_tasks(id_tasks);
break;
return;
}
size_t idx = result.data["index"];
@ -1827,6 +1826,13 @@ struct server_context {
for (server_slot & slot : slots) {
if (slot.ga_n == 1) {
if (slot.is_processing() && (int) system_tokens.size() + slot.n_past >= slot.n_ctx - 1) {
if (!params.ctx_shift){
slot.release();
slot.print_timings();
send_final_response(slot);
metrics.on_prediction(slot);
continue;
}
// 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;
@ -1952,6 +1958,12 @@ struct server_context {
send_final_response(slot);
continue;
}
// context shift is disabled and prompt is too large - discard it
if (!params.ctx_shift && (slot.n_prompt_tokens > slot.n_ctx) ){
slot.release();
send_error(slot, "Input is too large to process. Either enable context shift or increase the context length.", ERROR_TYPE_INVALID_REQUEST);
continue;
}
if (slot.cmpl_type == SERVER_TASK_CMPL_TYPE_EMBEDDING) {
// this prompt is too large to process - discard it