ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compiler warning and white space

Browse Source
This commit is contained in:
Kawrakow
2026-01-12 19:06:17 +02:00
parent c03c2d7cc6
commit d3e3ad40f9
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/server/server-context.cpp
View File

@@ -376,7 +376,7 @@ int server_slot::get_n_draft_max() const {
if (!ctx_dft) { if (!ctx_dft) {
return 0; return 0;
} }
// determine the max draft that fits the current slot state // determine the max draft that fits the current slot state
int n_draft_max = params.speculative.n_max; int n_draft_max = params.speculative.n_max;
@@ -2218,7 +2218,7 @@ void server_context::update_slots() {
slot.i_batch_dft.push_back(batch.n_tokens); slot.i_batch_dft.push_back(batch.n_tokens);
llama_batch_add(batch, slot.sampled, slot.cache_tokens.pos_next(), { slot.id }, true); llama_batch_add(batch, slot.sampled, slot.cache_tokens.pos_next(), { slot.id }, true);
slot.cache_tokens.push_back(slot.sampled); slot.cache_tokens.push_back(slot.sampled);
if (slot.params.speculative.n_min > (int)draft.size()) { if (slot.params.speculative.n_min > (int)draft.size()) {
SLT_DBG(slot, "ignoring small draft: %d < %d\n", (int)draft.size(), slot.params.speculative.n_min); SLT_DBG(slot, "ignoring small draft: %d < %d\n", (int)draft.size(), slot.params.speculative.n_min);
// fallback to normal decoding // fallback to normal decoding
@@ -2248,11 +2248,11 @@ void server_context::update_slots() {
slot.cache_tokens.push_back(slot.sampled); slot.cache_tokens.push_back(slot.sampled);
SLT_DBG(slot, "slot decode token, n_ctx = %d, n_tokens = %d, truncated = %d\n", SLT_DBG(slot, "slot decode token, n_ctx = %d, n_tokens = %d, truncated = %d\n",
slot.n_ctx, slot.cache_tokens.size(), slot.truncated); (int)slot.n_ctx, (int)slot.cache_tokens.size(), (int)slot.truncated);
} }
slot.n_past = slot.cache_tokens.n_tokens(); slot.n_past = slot.cache_tokens.n_tokens();
} }
// process in chunks of params.n_batch // process in chunks of params.n_batch
int32_t n_batch = llama_n_batch(ctx); int32_t n_batch = llama_n_batch(ctx);
int32_t n_ubatch = llama_n_ubatch(ctx); int32_t n_ubatch = llama_n_ubatch(ctx);
@@ -2391,7 +2391,7 @@ void server_context::update_slots() {
LLAMA_LOG_INFO("After context shift :\n"); LLAMA_LOG_INFO("After context shift :\n");
print_tokens(slot.prompt_tokens, slot.cache_tokens, prefix.second - back, prefix.first - back, 50); print_tokens(slot.prompt_tokens, slot.cache_tokens, prefix.second - back, prefix.first - back, 50);
} }
#endif #endif
} }
else { else {
slot.n_discarded_prompt = 0; slot.n_discarded_prompt = 0;