Merge branch 'ggml-org:master' into master

Author: Thireus

ggml/src/ggml-cpu/spacemit/ime.cpp

@@ -485,8 +485,9 @@ template <typename BLOC_TYPE, int64_t INTER_SIZE, int64_t NB_COLS> class tensor_
             int32_t          start                  = ith * task_per_thread;
             int32_t          end                    = std::min((ith + 1) * task_per_thread, task_count);
             for (int32_t compute_idx = start; compute_idx < end; compute_idx++) {
-                int32_t                             gemm_idx = compute_idx / block_size_m;
-                int32_t                             m_idx    = compute_idx % block_size_m * block_size_m;
+                int32_t                             gemm_idx = compute_idx / per_gemm_block_count_m;
+                int32_t                             block_idx_in_gemm = compute_idx % per_gemm_block_count_m;
+                int32_t                             m_idx    = block_idx_in_gemm * block_size_m;
                 const qnbitgemm_spacemit_ime_args & data     = qnbitgemm_args[gemm_idx];
                 int32_t rows_tobe_handled = (gemm_m - m_idx) > block_size_m ? block_size_m : (gemm_m - m_idx);
 

ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp

@@ -959,7 +959,7 @@ void write_output_files() {
     }
 
     std::string suffixes[2] = {"_f32", "_f16"};
-    for (auto op : {"add", "sub", "mul", "div", "add_rms"}) {
+    for (std::string op : {"add", "sub", "mul", "div", "add_rms"}) {
         hdr << "extern const void * " << op << "_data[2][2][2][2];\n";
         hdr << "extern const uint64_t " << op << "_len[2][2][2][2];\n";
 

tools/server/public/index.html.gz

@@ -4,7 +4,7 @@
 		Funnel,
 		AlertTriangle,
 		Brain,
-		Cog,
+		Code,
 		Monitor,
 		Sun,
 		Moon,
@@ -88,9 +88,59 @@
 			]
 		},
 		{
-			title: 'Samplers',
+			title: 'Sampling',
 			icon: Funnel,
 			fields: [
+				{
+					key: 'temperature',
+					label: 'Temperature',
+					type: 'input'
+				},
+				{
+					key: 'dynatemp_range',
+					label: 'Dynamic temperature range',
+					type: 'input'
+				},
+				{
+					key: 'dynatemp_exponent',
+					label: 'Dynamic temperature exponent',
+					type: 'input'
+				},
+				{
+					key: 'top_k',
+					label: 'Top K',
+					type: 'input'
+				},
+				{
+					key: 'top_p',
+					label: 'Top P',
+					type: 'input'
+				},
+				{
+					key: 'min_p',
+					label: 'Min P',
+					type: 'input'
+				},
+				{
+					key: 'xtc_probability',
+					label: 'XTC probability',
+					type: 'input'
+				},
+				{
+					key: 'xtc_threshold',
+					label: 'XTC threshold',
+					type: 'input'
+				},
+				{
+					key: 'typ_p',
+					label: 'Typical P',
+					type: 'input'
+				},
+				{
+					key: 'max_tokens',
+					label: 'Max tokens',
+					type: 'input'
+				},
 				{
 					key: 'samplers',
 					label: 'Samplers',
@@ -152,68 +202,17 @@
 					key: 'showThoughtInProgress',
 					label: 'Show thought in progress',
 					type: 'checkbox'
-				},
-				{
-					key: 'disableReasoningFormat',
-					label:
-						'Show raw LLM output without backend parsing and frontend Markdown rendering to inspect streaming across different models.',
-					type: 'checkbox'
 				}
 			]
 		},
 		{
-			title: 'Advanced',
-			icon: Cog,
+			title: 'Developer',
+			icon: Code,
 			fields: [
 				{
-					key: 'temperature',
-					label: 'Temperature',
-					type: 'input'
-				},
-				{
-					key: 'dynatemp_range',
-					label: 'Dynamic temperature range',
-					type: 'input'
-				},
-				{
-					key: 'dynatemp_exponent',
-					label: 'Dynamic temperature exponent',
-					type: 'input'
-				},
-				{
-					key: 'top_k',
-					label: 'Top K',
-					type: 'input'
-				},
-				{
-					key: 'top_p',
-					label: 'Top P',
-					type: 'input'
-				},
-				{
-					key: 'min_p',
-					label: 'Min P',
-					type: 'input'
-				},
-				{
-					key: 'xtc_probability',
-					label: 'XTC probability',
-					type: 'input'
-				},
-				{
-					key: 'xtc_threshold',
-					label: 'XTC threshold',
-					type: 'input'
-				},
-				{
-					key: 'typ_p',
-					label: 'Typical P',
-					type: 'input'
-				},
-				{
-					key: 'max_tokens',
-					label: 'Max tokens',
-					type: 'input'
+					key: 'disableReasoningFormat',
+					label: 'Show raw LLM output',
+					type: 'checkbox'
 				},
 				{
 					key: 'custom',