Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CONTRIBUTING.md
#	docs/backend/CANN.md
#	examples/eval-callback/eval-callback.cpp
#	examples/model-conversion/requirements.txt
#	examples/model-conversion/scripts/causal/run-org-model.py
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	models/templates/README.md
#	requirements/requirements-convert_hf_to_gguf.txt
#	requirements/requirements-convert_legacy_llama.txt
#	requirements/requirements-tool_bench.txt
#	tests/.gitignore
#	tests/test-backend-ops.cpp
#	tests/test-chat-parser.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-tokenizer-random.py

tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py

@@ -23,7 +23,6 @@ import warnings
 import numpy as np
 import torch
 import torch.nn.functional as F
-import torch.utils.checkpoint
 from torch import nn
 from torch.nn.init import _calculate_fan_in_and_fan_out
 
@@ -413,7 +412,8 @@ import re
 
 import numpy as np
 from gguf import *
-from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionTransformer, Idefics2VisionConfig
+from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionTransformer
+from transformers.models.idefics2.configuration_idefics2 import Idefics2VisionConfig
 
 TEXT = "clip.text"
 VISION = "clip.vision"

tools/mtmd/requirements.txt

@@ -1,5 +1,5 @@
 -r ../../requirements/requirements-convert_legacy_llama.txt
 --extra-index-url https://download.pytorch.org/whl/cpu
 pillow~=11.3.0
-torch~=2.4.0
-torchvision~=0.19.1
+torch~=2.6.0
+torchvision~=0.21.0

tools/server/public_legacy/json-schema-to-grammar.mjs

@@ -631,9 +631,10 @@ export class SchemaConverter {
       const required = new Set(schema.required || []);
       const properties = Object.entries(schema.properties ?? {});
       return this._addRule(ruleName, this._buildObjectRule(properties, required, name, schema.additionalProperties));
-    } else if ((schemaType === undefined || schemaType === 'object') && 'allOf' in schema) {
+    } else if ((schemaType === undefined || schemaType === 'object' || schemaType === 'string') && 'allOf' in schema) {
       const required = new Set();
       const properties = [];
+      const enumSets = [];
       const addComponent = (compSchema, isRequired) => {
         const ref = compSchema.$ref;
         if (ref !== undefined) {
@@ -648,6 +649,10 @@ export class SchemaConverter {
             }
           }
         }
+
+        if ('enum' in compSchema) {
+          enumSets.push(new Set(compSchema.enum || []));
+        }
       };
 
       for (const t of schema.allOf) {
@@ -660,6 +665,14 @@ export class SchemaConverter {
         }
       }
 
+      if (enumSets.length > 0) {
+        const enumIntersection = new Set([...enumSets[0]].filter(v => enumSets.every(s => s.has(v))));
+        if (enumIntersection.size > 0) {
+          const sortedEnums = [...enumIntersection].sort((a, b) => a.localeCompare(b));
+          const rule = '(' + sortedEnums.map(v => this._generateConstantRule(v)).join(' | ') + ') space';
+          return this._addRule(ruleName, rule);
+        }
+      }
       return this._addRule(ruleName, this._buildObjectRule(properties, required, name, null));
     } else if ((schemaType === undefined || schemaType === 'array') && ('items' in schema || 'prefixItems' in schema)) {
       const items = schema.items ?? schema.prefixItems;

tools/server/server.cpp

@@ -308,6 +308,7 @@ struct server_task {
 
         // enabling this will output extra debug information in the HTTP responses from the server
         params.verbose           = params_base.verbosity > 9;
+        params.timings_per_token = json_value(data, "timings_per_token", false);
 
         params.stream           = json_value(data, "stream",             false);
         params.cache_prompt     = json_value(data, "cache_prompt",       true);

tools/server/tests/requirements.txt

@@ -1,6 +1,6 @@
 aiohttp~=3.9.3
 pytest~=8.3.3
-huggingface_hub~=0.23.2
+huggingface_hub>=0.34.0,<1.0
 numpy~=1.26.4
 openai~=1.55.3
 prometheus-client~=0.20.0