Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	examples/model-conversion/requirements.txt
#	examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py
#	examples/speculative-simple/README.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	requirements/requirements-convert_hf_to_gguf.txt
#	requirements/requirements-convert_lora_to_gguf.txt
#	scripts/hip/gcn-cdna-vgpr-check.py
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/imatrix/imatrix.cpp
#	tools/mtmd/CMakeLists.txt

tools/server/server-context.cpp

@@ -397,12 +397,7 @@ struct server_slot {
 
     bool need_embd() const {
         GGML_ASSERT(task);
-        return task->need_embd() || (spec && common_speculative_need_embd(spec));
-    }
-
-    bool need_embd_nextn() const {
-        GGML_ASSERT(task);
-        return spec && common_speculative_need_embd_nextn(spec);
+        return task->need_embd();
     }
 
     // if the context does not have a memory module then all embeddings have to be computed within a single ubatch

tools/server/server-tools.cpp

@@ -1,6 +1,7 @@
 #include "server-tools.h"
 
 #include "subproc.h"
+#include "base64.hpp"
 
 #include <filesystem>
 #include <fstream>
@@ -864,6 +865,7 @@ static bool path_glob_match(const std::string & pattern, const std::string & rel
 //
 
 static constexpr size_t SERVER_TOOL_READ_FILE_MAX_SIZE = 16 * 1024; // 16 KB
+static constexpr size_t SERVER_TOOL_READ_FILE_MAX_SIZE_BASE64 = 32 * 1024 * 1024; // 32 MB
 
 struct server_tool_read_file : server_tool {
     server_tool_read_file() {
@@ -899,6 +901,8 @@ struct server_tool_read_file : server_tool {
         int  start_line   = json_value(params, "start_line", 1);
         int  end_line     = json_value(params, "end_line",  -1); // -1 = no limit
         bool append_loc   = json_value(params, "append_loc", false);
+        // comes from the x-resp-type header, the model cannot ask for it
+        bool as_base64    = json_value(params, "resp_type", std::string()) == "base64";
 
         auto io = make_tools_io(params);
 
@@ -906,6 +910,23 @@ struct server_tool_read_file : server_tool {
         if (!io->file_size(path, file_size)) {
             return {{"error", "cannot stat file: " + path}};
         }
+
+        if (as_base64) {
+            if (file_size > SERVER_TOOL_READ_FILE_MAX_SIZE_BASE64) {
+                return {{"error", string_format(
+                    "file too large (%zu bytes, max %zu)",
+                    (size_t)file_size, SERVER_TOOL_READ_FILE_MAX_SIZE_BASE64)}};
+            }
+            std::string content;
+            if (!io->read_file(path, content)) {
+                return {{"error", "failed to open file: " + path}};
+            }
+            return {
+                {"base64",     base64::encode(content.data(), content.size())},
+                {"size_bytes", (size_t) content.size()},
+            };
+        }
+
         if (file_size > SERVER_TOOL_READ_FILE_MAX_SIZE && end_line == -1) {
             return {{"error", string_format(
                 "file too large (%zu bytes, max %zu). Use start_line/end_line to read a portion.",
@@ -2135,6 +2156,15 @@ void server_tools::setup(const std::vector<std::string> & enabled_tools,
                 params["runtime"] = runtime->spec();
             }
 
+            // x-resp-type header is only used by read_file for now
+            if (params.contains("resp_type")) {
+                params.erase("resp_type");
+            }
+            auto resp_type = get_header(req.headers, "x-resp-type");
+            if (!resp_type.empty()) {
+                params["resp_type"] = resp_type;
+            }
+
             server_tool & tool = find_tool(tools, tool_name, stream);
 
             if (stream) {

tools/server/tests/unit/test_speculative.py

@@ -27,8 +27,8 @@ def test_with_and_without_draft():
     global server
     request = {
         "prompt": "I believe the meaning of life is",
-        "temperature": 0.8,
-        "top_k": 40,
+        "temperature": 0.2,
+        "top_k": 5,
         "seed": 4242,
         "n_predict": 16,
         "return_tokens": True,
@@ -36,7 +36,6 @@ def test_with_and_without_draft():
 
     server.model_draft = None  # disable draft model
     server.spec_type = None
-    server.backend_sampling = True
     server.start()
     res = server.make_request("POST", "/completion", data=request)
     assert res.status_code == 200
@@ -45,7 +44,6 @@ def test_with_and_without_draft():
 
     # create new server with draft model
     create_server()
-    server.backend_sampling = True
     server.start()
     res = server.make_request("POST", "/completion", data=request)
     assert res.status_code == 200