Merge commit 'd7f5f4e578d1f60b0835d1734a50438c309b3e5c' into concedo_experimental

# Conflicts:
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/labeler.yml
#	.github/workflows/build.yml
#	docs/docker.md
#	examples/simple-chat/simple-chat.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp

src/llama-kv-cache-unified-iswa.cpp

@@ -250,7 +250,7 @@ bool llama_kv_cache_unified_iswa_context::next() {
 }
 
 bool llama_kv_cache_unified_iswa_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     bool res = true;
 

src/llama-kv-cache-unified.cpp

@@ -1776,7 +1776,7 @@ bool llama_kv_cache_unified_context::next() {
 }
 
 bool llama_kv_cache_unified_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     // no ubatches -> this is a KV cache update
     if (ubatches.empty()) {

src/llama-memory-hybrid.cpp

@@ -218,7 +218,7 @@ bool llama_memory_hybrid_context::next() {
 }
 
 bool llama_memory_hybrid_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     bool res = true;
 

src/llama-memory-recurrent.cpp

@@ -1071,7 +1071,15 @@ bool llama_memory_recurrent_context::next() {
 }
 
 bool llama_memory_recurrent_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
+
+    // no ubatches -> this is an update
+    if (ubatches.empty()) {
+        // recurrent cache never performs updates
+        assert(status == LLAMA_MEMORY_STATUS_NO_UPDATE);
+
+        return true;
+    }
 
     mem->find_slot(ubatches[i_next]);
 

src/llama-memory.cpp

@@ -40,3 +40,20 @@ llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_me
     // if either status has an update, then the combined status has an update
     return has_update ? LLAMA_MEMORY_STATUS_SUCCESS : LLAMA_MEMORY_STATUS_NO_UPDATE;
 }
+
+bool llama_memory_status_is_fail(llama_memory_status status) {
+    switch (status) {
+        case LLAMA_MEMORY_STATUS_SUCCESS:
+        case LLAMA_MEMORY_STATUS_NO_UPDATE:
+            {
+                return false;
+            }
+        case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
+        case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
+            {
+                return true;
+            }
+    }
+
+    return false;
+}

src/llama-memory.h

@@ -31,6 +31,9 @@ enum llama_memory_status {
 // useful for implementing hybrid memory types (e.g. iSWA)
 llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1);
 
+// helper function for checking if a memory status indicates a failure
+bool llama_memory_status_is_fail(llama_memory_status status);
+
 // the interface for managing the memory context during batch processing
 // this interface is implemented per memory type. see:
 //   - llama_kv_cache_unified_context