Merge branch 'upstream' into concedo_experimental

# Conflicts: # .devops/full-cuda.Dockerfile # .devops/llama-cli-cann.Dockerfile # .devops/llama-cli-cuda.Dockerfile # .devops/llama-cli-intel.Dockerfile # .devops/llama-cli-musa.Dockerfile # .devops/llama-cli-vulkan.Dockerfile # .devops/llama-server-cuda.Dockerfile # .devops/llama-server-intel.Dockerfile # .devops/llama-server-musa.Dockerfile # .devops/llama-server-vulkan.Dockerfile # .gitignore # CMakeLists.txt # Makefile # cmake/llama-config.cmake.in # docs/backend/SYCL.md # docs/build.md # examples/llama-bench/llama-bench.cpp # flake.lock # ggml/CMakeLists.txt # ggml/src/CMakeLists.txt # ggml/src/ggml-backend.cpp # ggml/src/ggml-blas/CMakeLists.txt # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-cpu/ggml-cpu.c # ggml/src/ggml-cuda/CMakeLists.txt # ggml/src/ggml-hip/CMakeLists.txt # ggml/src/ggml-metal/CMakeLists.txt # ggml/src/ggml-musa/CMakeLists.txt # ggml/src/ggml-sycl/CMakeLists.txt # scripts/sync-ggml.last # tests/test-backend-ops.cpp
LostRuins · Nov 21, 2024 · 091a432 · 091a432
2 parents 282a647 + 87a533b
commit 091a432
Show file tree

Hide file tree

Showing 38 changed files with 188,983 additions and 158,244 deletions.
diff --git a/.clang-format b/.clang-format
@@ -0,0 +1,161 @@
+---
+Language:        Cpp
+AlignAfterOpenBracket: Align
+AlignArrayOfStructures: Left
+AlignConsecutiveAssignments: AcrossComments
+AlignConsecutiveBitFields: AcrossComments
+AlignConsecutiveDeclarations: AcrossComments
+AlignConsecutiveMacros: AcrossComments
+# AlignConsecutiveShortCaseStatements: AcrossComments
+AlignEscapedNewlines: Left # LeftWithLastLine
+AlignOperands:   Align
+AlignTrailingComments:
+  Kind: Always
+  OverEmptyLines: 1
+AllowAllArgumentsOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: false
+# AllowBreakBeforeNoexceptSpecifier: OnlyWithParen
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Inline
+AllowShortIfStatementsOnASingleLine: Never
+AllowShortLambdasOnASingleLine: Inline
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakBeforeMultilineStrings: true
+BinPackArguments: true
+BinPackParameters: true # OnePerLine
+BitFieldColonSpacing: Both
+BreakBeforeBraces: Custom # Attach
+BraceWrapping:
+  AfterCaseLabel:  true
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  AfterExternBlock: false
+  BeforeCatch:     false
+  BeforeElse:      false
+  BeforeLambdaBody: false
+  BeforeWhile: false
+  IndentBraces:    false
+  SplitEmptyFunction: false
+  SplitEmptyRecord: false
+  SplitEmptyNamespace: false
+# BreakAdjacentStringLiterals: true
+BreakAfterAttributes: Never
+BreakBeforeBinaryOperators: None
+BreakBeforeInlineASMColon: OnlyMultiline
+BreakBeforeTernaryOperators: false
+# BreakBinaryOperations: Never
+BreakConstructorInitializers: AfterColon
+# BreakFunctionDefinitionParameters: false
+BreakInheritanceList: AfterComma
+BreakStringLiterals: true
+# BreakTemplateDeclarations: Yes
+ColumnLimit:     120
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: false
+DerivePointerAlignment: false
+DisableFormat:   false
+EmptyLineBeforeAccessModifier: Leave
+EmptyLineAfterAccessModifier: Never
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+IncludeBlocks:   Regroup
+IncludeCategories:
+  - Regex:           '^<.*\.h>'
+    Priority:        1
+    SortPriority:    0
+  - Regex:           '^<.*'
+    Priority:        2
+    SortPriority:    0
+  - Regex:           '.*'
+    Priority:        3
+    SortPriority:    0
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeIsMainSourceRegex: ''
+IndentAccessModifiers: false
+IndentCaseBlocks: true
+IndentCaseLabels: true
+IndentExternBlock: NoIndent
+IndentGotoLabels: false
+IndentPPDirectives: AfterHash
+IndentWidth:     4
+IndentWrappedFunctionNames: false
+InsertBraces:    true # NOTE: may lead to incorrect formatting
+InsertNewlineAtEOF: true
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+LambdaBodyIndentation: Signature
+LineEnding: LF
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Auto
+ObjCBlockIndentWidth: 4
+ObjCSpaceAfterProperty: true
+ObjCSpaceBeforeProtocolList: true
+PPIndentWidth: -1
+PackConstructorInitializers: CurrentLine
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Middle
+QualifierAlignment: Left
+#QualifierOrder: ['static', 'inline', 'friend', 'constexpr', 'const', 'volatile', 'type', 'restrict']
+RawStringFormats:
+  - Language:        Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+ReferenceAlignment: Middle
+ReflowComments:  false # IndentOnly
+SeparateDefinitionBlocks: Always
+SortIncludes:    CaseInsensitive
+SortUsingDeclarations: LexicographicNumeric
+SpaceAfterCStyleCast: true
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles:  Never
+SpacesInContainerLiterals: true
+SpacesInLineCommentPrefix:
+  Minimum: 1
+  Maximum: -1
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+SpaceBeforeSquareBrackets: false
+Standard:        c++17
+TabWidth:        4
+UseTab:          Never
+WhitespaceSensitiveMacros: ['STRINGIZE']
+...
+
diff --git a/.devops/full-musa.Dockerfile b/.devops/full-musa.Dockerfile
diff --git a/common/common.cpp b/common/common.cpp
@@ -877,6 +877,12 @@ struct common_init_result common_init_from_params(common_params & params) {
         return iparams;
     }
 
+    if (params.ctx_shift && !llama_kv_cache_can_shift(lctx)) {
+        LOG_ERR("%s: KV cache shifting is not supported for this model (--no-context-shift to disable)'\n", __func__);
+        llama_free_model(model);
+        return iparams;
+    }
+
     if (!params.control_vectors.empty()) {
         if (params.control_vector_layer_start <= 0) params.control_vector_layer_start = 1;
         if (params.control_vector_layer_end   <= 0) params.control_vector_layer_end   = llama_n_layer(model);

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
@@ -3040,6 +3040,11 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         return [(self.map_tensor_name(name), data_torch)]
 
 
+@Model.register("Olmo1124ForCausalLM")
+class Olmo1124Model(Model):
+    model_arch = gguf.MODEL_ARCH.OLMO_1124
+
+
 @Model.register("OlmoeForCausalLM")
 class OlmoeModel(Model):
     model_arch = gguf.MODEL_ARCH.OLMOE

diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp
@@ -252,6 +252,7 @@ void ggml_backend_tensor_get_async(ggml_backend_t backend, const struct ggml_ten
 }
 
 void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void * data, size_t offset, size_t size) {
+    GGML_ASSERT(tensor);
     ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
 
     if (size == 0) {
@@ -266,6 +267,7 @@ void ggml_backend_tensor_set(struct ggml_tensor * tensor, const void * data, siz
 }
 
 void ggml_backend_tensor_get(const struct ggml_tensor * tensor, void * data, size_t offset, size_t size) {
+    GGML_ASSERT(tensor);
     ggml_backend_buffer_t buf = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
 
     if (size == 0) {
@@ -689,7 +691,7 @@ static int ggml_backend_sched_backend_id(ggml_backend_sched_t sched, ggml_backen
 }
 
 static int ggml_backend_sched_backend_from_buffer(ggml_backend_sched_t sched, const struct ggml_tensor * tensor, const struct ggml_tensor * op) {
-    ggml_backend_buffer_t buffer = tensor->buffer;
+    ggml_backend_buffer_t buffer = tensor->view_src ? tensor->view_src->buffer : tensor->buffer;
     if (buffer == NULL) {
         return -1;
     }
@@ -724,8 +726,6 @@ static bool backend_prealloc_warn = false;
 
 // returns the backend that should be used for the node based on the current locations
 static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, struct ggml_tensor * tensor) {
-    // TODO: use supports_op to check if the backend supports the op
-
     // assign pre-allocated nodes to their backend
     int cur_backend_id = ggml_backend_sched_backend_from_buffer(sched, tensor, tensor);
     if (cur_backend_id != -1) {
@@ -747,7 +747,7 @@ static int ggml_backend_sched_backend_id_from_cur(ggml_backend_sched_t sched, st
         if(!backend_prealloc_warn)
         {
             backend_prealloc_warn = true;
-            printf("\nCaution: pre-allocated tensor in a backend that cannot run the operation\n");
+            printf("\nCaution: pre-allocated tensor (%s) in a backend that cannot run the operation\n", tensor->name);
         }
     }
 

diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
@@ -2372,15 +2372,15 @@ void ggml_numa_init(enum ggml_numa_strategy numa_flag) {
     // figure out which node we're on
     uint current_cpu;
     int getcpu_ret = 0;
-// #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 28) || defined(__COSMOPOLITAN__)
-//     getcpu_ret = getcpu(&current_cpu, &g_state.numa.current_node);
-// #else
-//     // old glibc doesn't have a wrapper for this call. Fall back on direct syscall
-// #   if !defined(SYS_getcpu) && defined(SYS_get_cpu)
-// #       define SYS_getcpu SYS_get_cpu // some older glibc versions use this name
-// #   endif
-//     getcpu_ret = syscall(SYS_getcpu, &current_cpu, &g_state.numa.current_node);
-// #endif
+//#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 33) || defined(__COSMOPOLITAN__)
+//    getcpu_ret = getcpu(&current_cpu, &g_state.numa.current_node);
+//#else
+//    // old glibc doesn't have a wrapper for this call. Fall back on direct syscall
+//#   if !defined(SYS_getcpu) && defined(SYS_get_cpu)
+//#       define SYS_getcpu SYS_get_cpu // some older glibc versions use this name
+//#   endif
+//    getcpu_ret = syscall(SYS_getcpu, &current_cpu, &g_state.numa.current_node);
+//#endif
 // koboldcpp fix: we don't use numa and this thing breaks runpod
 
     if (g_state.numa.n_nodes < 1 || g_state.numa.total_cpus < 1 || getcpu_ret != 0) {