CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-09 10:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : support unified cache across slots (#16736)

Browse Source 
* server : support unified context across slots

* cont : fix speculative decoding initialization

* context : fix n_ctx_per_seq computation

* server : purge slots one by one

* tests : add unified cache server tests

* llama : update per-seq context computation

* test-thread-safety : handle tiny training context of the input model

* server : fix server_tokens clear()

* server : use 4 slots + unified KV by default

* llama : add note about context size queries

* cont : update todos [no ci]

* context : do not cap the size of the context

* tests : adjust parameters to be CI friendlier

* context : add warning
This commit is contained in:
Georgi Gerganov
2025-11-02 18:14:04 +02:00
committed by GitHub
parent 87c9efc3b2
commit cd5e3b5754
12 changed files with 163 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/test-thread-safety.cpp
View File

@@ -131,7 +131,14 @@ int main(int argc, char ** argv) {
}
batch = llama_batch_get_one(&token, 1);
if (llama_decode(ctx.get(), batch)) {
int ret = llama_decode(ctx.get(), batch);
if (ret == 1 && i > 0) {
LOG_INF("Context full, stopping generation.\n");
break;
}
if (ret != 0) {
LOG_ERR("Model %d/%d, Context %d/%d: failed to decode\n", m + 1, num_models, c + 1, num_contexts);
failed.store(true);
return;