Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	examples/simple-chat/simple-chat.cpp
#	src/llama-quant.cpp
#	tools/run/run.cpp
#	tools/server/README.md

tools/server/server.cpp

@@ -3418,9 +3418,12 @@ struct server_context {
                     }
 
                     if (ret < -1) {
+                        // TODO: update slot state based on llama_memory_seq_pos_min() and llama_memory_seq_pos_max()
                         err = "Compute error.";
                     }
 
+                    // TODO: handle ret == 2 (abort) when we start aborting
+
                     if (!err.empty()) {
                         SRV_ERR("%s, i = %d, n_batch = %d, ret = %d\n", err.c_str(), i, n_batch, ret);
                         for (auto & slot : slots) {