server : fix extra BOS in infill endpoint (#11106)

* server : fix extra BOS in infill endpoing ggml-ci * server : update infill tests
ggerganov · Jan 6, 2025 · e6e7c75 · e6e7c75
1 parent 09186fa
commit e6e7c75
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
@@ -3797,7 +3797,7 @@ int main(int argc, char ** argv) {
         data["input_extra"] = input_extra; // default to empty array if it's not exist
 
         std::string prompt = json_value(data, "prompt", std::string());
-        std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, true, true);
+        std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, false, true);
         SRV_DBG("creating infill tasks, n_prompts = %d\n", (int) tokenized_prompts.size());
         data["prompt"] = format_infill(
             ctx_server.ctx,

diff --git a/examples/server/tests/unit/test_infill.py b/examples/server/tests/unit/test_infill.py
@@ -18,7 +18,7 @@ def test_infill_without_input_extra():
         "input_suffix": "}\n",
     })
     assert res.status_code == 200
-    assert match_regex("(Ann|small|shiny)+", res.body["content"])
+    assert match_regex("(Ann|small|shiny|Daddy)+", res.body["content"])
 
 
 def test_infill_with_input_extra():