nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

Browse Source 
* mtmd: add "placeholder bitmap" for counting tokens w/o preprocessing

* fast path skip preproc for placeholder

* fix build

* correct the api

* add server endpoint + tests

* add object name

* update docs

* add proxy handling

* fix build

* fix audio input path

* use is_placeholder in process_mtmd_prompt()

* nits

* nits (2)

* docs: clarify chat/completions/input_tokens is not official

* fix merge problem
This commit is contained in:
Xuan-Son Nguyen
2026-06-06 11:06:51 +02:00
committed by GitHub
parent 5a69c97439
commit f5c6ae1827
26 changed files with 732 additions and 422 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tools/server/server.cpp
View File

@@ -161,6 +161,8 @@ int llama_server(int argc, char ** argv) {
routes.post_tokenize = models_routes->proxy_post;
routes.post_detokenize = models_routes->proxy_post;
routes.post_apply_template = models_routes->proxy_post;
routes.post_chat_completions_tok = models_routes->proxy_post;
routes.post_responses_tok_oai = models_routes->proxy_post;
routes.get_lora_adapters = models_routes->proxy_get;
routes.post_lora_adapters = models_routes->proxy_post;
routes.get_slots = models_routes->proxy_get;
@@ -192,7 +194,6 @@ int llama_server(int argc, char ** argv) {
ctx_http.post("/v1/audio/transcriptions", ex_wrapper(routes.post_transcriptions_oai));
ctx_http.post("/audio/transcriptions", ex_wrapper(routes.post_transcriptions_oai));
ctx_http.post("/v1/messages", ex_wrapper(routes.post_anthropic_messages)); // anthropic messages API
ctx_http.post("/v1/messages/count_tokens", ex_wrapper(routes.post_anthropic_count_tokens)); // anthropic token counting
ctx_http.post("/infill", ex_wrapper(routes.post_infill));
ctx_http.post("/embedding", ex_wrapper(routes.post_embeddings)); // legacy
ctx_http.post("/embeddings", ex_wrapper(routes.post_embeddings));
@@ -204,6 +205,12 @@ int llama_server(int argc, char ** argv) {
ctx_http.post("/tokenize", ex_wrapper(routes.post_tokenize));
ctx_http.post("/detokenize", ex_wrapper(routes.post_detokenize));
ctx_http.post("/apply-template", ex_wrapper(routes.post_apply_template));
// token counting
ctx_http.post("/chat/completions/input_tokens", ex_wrapper(routes.post_chat_completions_tok));
ctx_http.post("/v1/chat/completions/input_tokens", ex_wrapper(routes.post_chat_completions_tok));
ctx_http.post("/responses/input_tokens", ex_wrapper(routes.post_responses_tok_oai));
ctx_http.post("/v1/responses/input_tokens", ex_wrapper(routes.post_responses_tok_oai));
ctx_http.post("/v1/messages/count_tokens", ex_wrapper(routes.post_anthropic_count_tokens)); // anthropic token counting
// LoRA adapters hotswap
ctx_http.get ("/lora-adapters", ex_wrapper(routes.get_lora_adapters));
ctx_http.post("/lora-adapters", ex_wrapper(routes.post_lora_adapters));