chore(trtllm): remove unused method

backends/trtllm/include/backend.h

@@ -72,12 +72,6 @@ namespace huggingface::tgi::backends {
                 const std::filesystem::path &executorWorker
         );
 
-        /**
-         * Query the executor for the number of token available for pulling
-         * @return
-         */
-        [[nodiscard]] size_t NumResponsesReady() const;
-
         /**
          * Submit a new generation task to the executor
          * @param tokens

backends/trtllm/lib/backend.cpp

@@ -102,17 +102,6 @@ huggingface::tgi::backends::TensorRtLlmBackend::TensorRtLlmBackend(
     SPDLOG_INFO(FMT_STRING("Engine (version={})"), config["/version"_json_pointer].get_ref<const std::string &>());
 }
 
-[[nodiscard("Returned number of requests needs to be consumed")]]
-size_t huggingface::tgi::backends::TensorRtLlmBackend::NumResponsesReady() const {
-    const auto numResponses = executor.getNumResponsesReady();
-
-#ifndef NDEBUG
-    if(numResponses > 0) SPDLOG_INFO(FMT_STRING("Num responses ready: {:d}"), numResponses);
-#endif
-
-    return numResponses;
-}
-
 [[nodiscard("Returned request id needs to be provided back to gather generated tokens")]]
 tle::IdType huggingface::tgi::backends::TensorRtLlmBackend::Submit(
         const std::vector<tle::TokenIdType> &tokens,
@@ -138,7 +127,8 @@ tle::IdType huggingface::tgi::backends::TensorRtLlmBackend::Submit(
 
 #ifndef NDEBUG
     SPDLOG_INFO(
-        FMT_STRING("Sampling config: topK={:d}, topP={:d}, temperature={:d}, repetition_penalty={:d}, frequency_penalty={:d}, seed={:d}"),
+            FMT_STRING(
+                    "Sampling config: topK={:d}, topP={:d}, temperature={:d}, repetition_penalty={:d}, frequency_penalty={:d}, seed={:d}"),
             topK, topP, temperature, repetition_penalty, frequency_penalty, seed
     )
             SPDLOG_INFO(FMT_STRING("Asking for max_new_tokens={:d}"), maxNewTokensChecked);