llama-cpp-bin 9563.0.0__tar.gz → 9568.0.0__tar.gz

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama-cpp-bin
-Version: 9563.0.0
+Version: 9568.0.0
 Summary: llama.cpp server binary built from source
 Author-email: Vladyslav Tkachenko <vladlearns@gmail.com>
 License: AGPL-3.0-or-later

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp

@@ -448,15 +448,19 @@ struct ggml_webgpu_upscale_pipeline_key_hash {
 /** Concat **/
 
 struct ggml_webgpu_concat_pipeline_key {
-    int type;
+    int  type;
+    bool src_overlap;
 
-    bool operator==(const ggml_webgpu_concat_pipeline_key & other) const { return type == other.type; }
+    bool operator==(const ggml_webgpu_concat_pipeline_key & other) const {
+        return type == other.type && src_overlap == other.src_overlap;
+    }
 };
 
 struct ggml_webgpu_concat_pipeline_key_hash {
     size_t operator()(const ggml_webgpu_concat_pipeline_key & key) const {
         size_t seed = 0;
         ggml_webgpu_hash_combine(seed, key.type);
+        ggml_webgpu_hash_combine(seed, key.src_overlap);
         return seed;
     }
 };
@@ -2634,6 +2638,7 @@ class ggml_webgpu_shader_lib {
     webgpu_pipeline get_concat_pipeline(const ggml_webgpu_shader_lib_context & context) {
         ggml_webgpu_concat_pipeline_key key = {};
         key.type                            = context.dst->type;
+        key.src_overlap                     = ggml_webgpu_tensor_overlap(context.src0, context.src1);
 
         auto it = concat_pipelines.find(key);
         if (it != concat_pipelines.end()) {
@@ -2656,11 +2661,17 @@ class ggml_webgpu_shader_lib {
                 GGML_ABORT("Unsupported type for concat shader");
         }
 
+        if (key.src_overlap) {
+            defines.push_back("SRC_OVERLAP");
+            variant += "_src_overlap";
+        }
+
         defines.push_back(std::string("WG_SIZE=") + std::to_string(context.max_wg_size));
 
         auto processed           = preprocessor.preprocess(wgsl_concat, defines);
-        auto decisions           = std::make_shared<ggml_webgpu_generic_shader_decisions>();
+        auto decisions           = std::make_shared<ggml_webgpu_binary_shader_decisions>();
         decisions->wg_size       = context.max_wg_size;
+        decisions->src_overlap   = key.src_overlap;
         webgpu_pipeline pipeline = ggml_webgpu_create_pipeline(device, processed, variant);
         pipeline.context         = decisions;
         concat_pipelines[key]    = pipeline;

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/ggml/src/ggml-webgpu/ggml-webgpu.cpp

@@ -621,10 +621,11 @@ static void ggml_backend_webgpu_buffer_memset(webgpu_global_context & ctx,
                                               uint32_t                value,
                                               size_t                  offset,
                                               size_t                  size) {
-    std::vector<uint32_t>             params       = { (uint32_t) offset, (uint32_t) size, value };
-    std::vector<wgpu::BindGroupEntry> entries      = { ggml_webgpu_make_bind_group_entry(0, buf, 0, buf.GetSize()) };
-    size_t                            bytes_per_wg = ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup * ctx->capabilities.memset_bytes_per_thread;
-    uint32_t                          wg_x         = CEIL_DIV(size + 3, bytes_per_wg);
+    std::vector<uint32_t>             params  = { (uint32_t) offset, (uint32_t) size, value };
+    std::vector<wgpu::BindGroupEntry> entries = { ggml_webgpu_make_bind_group_entry(0, buf, 0, buf.GetSize()) };
+    size_t                            bytes_per_wg =
+        ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup * ctx->capabilities.memset_bytes_per_thread;
+    uint32_t wg_x = CEIL_DIV(size + 3, bytes_per_wg);
 
     ctx->queue.WriteBuffer(ctx->memset_params_buf, 0, params.data(), params.size() * sizeof(uint32_t));
 
@@ -1362,7 +1363,7 @@ static webgpu_encoded_op ggml_webgpu_get_rows(webgpu_context & ctx,
     shader_lib_ctx.src0                           = src;
     shader_lib_ctx.src1                           = nullptr;
     shader_lib_ctx.dst                            = dst;
-    shader_lib_ctx.max_wg_size                    = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
+    shader_lib_ctx.max_wg_size = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
 
     webgpu_pipeline pipeline  = ctx->shader_lib->get_get_rows_pipeline(shader_lib_ctx);
     auto *          decisions = static_cast<ggml_webgpu_generic_shader_decisions *>(pipeline.context.get());
@@ -2169,8 +2170,10 @@ static webgpu_encoded_op ggml_webgpu_unary_op(webgpu_context & ctx, ggml_tensor
         entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, dst));
     }
 
-    uint32_t wg_x = CEIL_DIV(ne, decisions->wg_size);
-    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x);
+    uint32_t wg_x, wg_y;
+    uint32_t total_wg = CEIL_DIV(ggml_nelements(dst), decisions->wg_size);
+    compute_2d_workgroups(total_wg, ctx->global_ctx->capabilities.limits.maxComputeWorkgroupsPerDimension, wg_x, wg_y);
+    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
 }
 
 static webgpu_encoded_op ggml_webgpu_binary_op(webgpu_context & ctx,
@@ -2244,8 +2247,10 @@ static webgpu_encoded_op ggml_webgpu_binary_op(webgpu_context & ctx,
         }
     }
 
-    uint32_t wg_x = CEIL_DIV(ne, decisions->wg_size);
-    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x);
+    uint32_t wg_x, wg_y;
+    uint32_t total_wg = CEIL_DIV(ggml_nelements(dst), decisions->wg_size);
+    compute_2d_workgroups(total_wg, ctx->global_ctx->capabilities.limits.maxComputeWorkgroupsPerDimension, wg_x, wg_y);
+    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
 }
 
 static webgpu_encoded_op ggml_webgpu_add_id(webgpu_context & ctx,
@@ -2305,33 +2310,6 @@ static webgpu_encoded_op ggml_webgpu_concat(webgpu_context & ctx,
     uint32_t ne  = (uint32_t) ggml_nelements(dst);
     uint32_t dim = (uint32_t) dst->op_params[0];
 
-    std::vector<uint32_t> params = {
-        ne,
-        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src0) / ggml_type_size(src0->type)),
-        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src1) / ggml_type_size(src1->type)),
-        (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
-        (uint32_t) (src0->nb[0] / ggml_type_size(src0->type)),
-        (uint32_t) (src0->nb[1] / ggml_type_size(src0->type)),
-        (uint32_t) (src0->nb[2] / ggml_type_size(src0->type)),
-        (uint32_t) (src0->nb[3] / ggml_type_size(src0->type)),
-        (uint32_t) (src1->nb[0] / ggml_type_size(src1->type)),
-        (uint32_t) (src1->nb[1] / ggml_type_size(src1->type)),
-        (uint32_t) (src1->nb[2] / ggml_type_size(src1->type)),
-        (uint32_t) (src1->nb[3] / ggml_type_size(src1->type)),
-        (uint32_t) dst->ne[0],
-        (uint32_t) dst->ne[1],
-        (uint32_t) dst->ne[2],
-        (uint32_t) dst->ne[3],
-        dim,
-        (uint32_t) src0->ne[dim]
-    };
-
-    std::vector<wgpu::BindGroupEntry> entries = {
-        ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src0),
-        ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, src1),
-        ggml_webgpu_make_tensor_bind_group_entry(ctx, 2, dst),
-    };
-
     ggml_webgpu_shader_lib_context shader_lib_ctx = {};
     shader_lib_ctx.src0                           = src0;
     shader_lib_ctx.src1                           = src1;
@@ -2339,8 +2317,52 @@ static webgpu_encoded_op ggml_webgpu_concat(webgpu_context & ctx,
     shader_lib_ctx.max_wg_size = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
 
     webgpu_pipeline pipeline  = ctx->shader_lib->get_concat_pipeline(shader_lib_ctx);
-    auto *          decisions = static_cast<ggml_webgpu_generic_shader_decisions *>(pipeline.context.get());
-    uint32_t        wg_x      = CEIL_DIV(ne, decisions->wg_size);
+    auto *          decisions = static_cast<ggml_webgpu_binary_shader_decisions *>(pipeline.context.get());
+
+    uint32_t offset_src0   = (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src0) / ggml_type_size(src0->type));
+    uint32_t offset_src1   = (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src1) / ggml_type_size(src1->type));
+    size_t   merged_offset = 0;
+    size_t   merged_size   = 0;
+    if (decisions->src_overlap) {
+        const ggml_webgpu_merged_binding_range merged_range =
+            ggml_webgpu_tensor_merged_binding_range(ctx, { src0, src1 });
+        merged_offset = merged_range.offset;
+        merged_size   = merged_range.size;
+        offset_src0   = ggml_webgpu_tensor_merged_element_offset(src0, merged_range);
+        offset_src1   = ggml_webgpu_tensor_merged_element_offset(src1, merged_range);
+    }
+
+    std::vector<uint32_t> params = { ne,
+                                     offset_src0,
+                                     offset_src1,
+                                     (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
+                                     (uint32_t) (src0->nb[0] / ggml_type_size(src0->type)),
+                                     (uint32_t) (src0->nb[1] / ggml_type_size(src0->type)),
+                                     (uint32_t) (src0->nb[2] / ggml_type_size(src0->type)),
+                                     (uint32_t) (src0->nb[3] / ggml_type_size(src0->type)),
+                                     (uint32_t) (src1->nb[0] / ggml_type_size(src1->type)),
+                                     (uint32_t) (src1->nb[1] / ggml_type_size(src1->type)),
+                                     (uint32_t) (src1->nb[2] / ggml_type_size(src1->type)),
+                                     (uint32_t) (src1->nb[3] / ggml_type_size(src1->type)),
+                                     (uint32_t) dst->ne[0],
+                                     (uint32_t) dst->ne[1],
+                                     (uint32_t) dst->ne[2],
+                                     (uint32_t) dst->ne[3],
+                                     dim,
+                                     (uint32_t) src0->ne[dim] };
+
+    std::vector<wgpu::BindGroupEntry> entries = {};
+    if (decisions->src_overlap) {
+        entries.push_back(
+            ggml_webgpu_make_bind_group_entry(0, ggml_webgpu_tensor_buf(src0), merged_offset, merged_size));
+        entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, dst));
+    } else {
+        entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src0));
+        entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, src1));
+        entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 2, dst));
+    }
+
+    uint32_t wg_x = CEIL_DIV(ne, decisions->wg_size);
     return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x);
 }
 
@@ -2673,8 +2695,10 @@ static webgpu_encoded_op ggml_webgpu_scale(webgpu_context & ctx, ggml_tensor * s
         entries.push_back(ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, dst));
     }
 
-    uint32_t wg_x = CEIL_DIV(ggml_nelements(dst), decisions->wg_size);
-    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x);
+    uint32_t wg_x, wg_y;
+    uint32_t total_wg = CEIL_DIV(ggml_nelements(dst), decisions->wg_size);
+    compute_2d_workgroups(total_wg, ctx->global_ctx->capabilities.limits.maxComputeWorkgroupsPerDimension, wg_x, wg_y);
+    return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
 }
 
 static webgpu_encoded_op ggml_webgpu_soft_max(webgpu_context & ctx,
@@ -3751,7 +3775,8 @@ static ggml_guid_t ggml_backend_webgpu_guid(void) {
 
 static void ggml_webgpu_init_memset_pipeline(webgpu_global_context & ctx) {
     // we use the maximum workgroup size for the memset pipeline
-    size_t max_threads = ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup * ctx->capabilities.limits.maxComputeWorkgroupsPerDimension;
+    size_t max_threads = ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup *
+                         ctx->capabilities.limits.maxComputeWorkgroupsPerDimension;
     // Size the bytes_per_thread so that the largest buffer size can be handled
     ctx->capabilities.memset_bytes_per_thread =
         CEIL_DIV(ctx->capabilities.limits.maxStorageBufferBindingSize, max_threads);

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/src/llama-arch.cpp

@@ -559,6 +559,8 @@ static const std::map<llm_tensor, const char *> LLM_TENSOR_NAMES = {
     { LLM_TENSOR_INDEXER_PROJ,                           "blk.%d.indexer.proj" },
     { LLM_TENSOR_INDEXER_ATTN_K,                         "blk.%d.indexer.attn_k" },
     { LLM_TENSOR_INDEXER_ATTN_Q_B,                       "blk.%d.indexer.attn_q_b" },
+    { LLM_TENSOR_MASKED_EMBD_CENTROIDS,                  "masked_embd_centroids" },
+    { LLM_TENSOR_MASKED_EMBD_ORDERING,                   "masked_embd_ordering" },
 };
 
 // declare information about the model weight tensors:
@@ -783,6 +785,8 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
     // latent projections feed ggml_mul_mat, the buft probe must use MUL_MAT to keep them on GPU
     {LLM_TENSOR_FFN_LATENT_DOWN,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
     {LLM_TENSOR_FFN_LATENT_UP,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
+    {LLM_TENSOR_MASKED_EMBD_CENTROIDS,      {LLM_TENSOR_LAYER_INPUT,     GGML_OP_NONE}},
+    {LLM_TENSOR_MASKED_EMBD_ORDERING,       {LLM_TENSOR_LAYER_INPUT,     GGML_OP_NONE}},
 };
 
 LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {}

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/src/llama-arch.h

@@ -566,8 +566,11 @@ enum llm_tensor {
     LLM_TENSOR_NEXTN_HNORM,
     LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD,
     LLM_TENSOR_NEXTN_SHARED_HEAD_NORM,
+    LLM_TENSOR_MASKED_EMBD_CENTROIDS,
+    LLM_TENSOR_MASKED_EMBD_ORDERING,
 };
 
+
 enum llm_tensor_layer {
     LLM_TENSOR_LAYER_INPUT,
     LLM_TENSOR_LAYER_REPEATING,

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/src/llama-graph.cpp

@@ -567,7 +567,10 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
         mctx->get_base()->set_input_v_idxs(self_v_idxs, ubatch);
     }
 
-    mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
+    // the kq mask guards on its own buffer: shared cells leave idxs unbacked while the mask stays live
+    if (self_kq_mask && self_kq_mask->buffer) {
+        mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
+    }
 
     // swa tensors may not be allocated if there are no SWA attention layers
     if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -575,7 +578,9 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
         mctx->get_swa()->set_input_v_idxs(self_v_idxs_swa, ubatch);
     }
 
-    mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
+    if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
+        mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
+    }
 
     if (self_k_rot) {
         mctx->get_base()->set_input_k_rot(self_k_rot);
@@ -607,7 +612,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
       //res &= self_v_idxs->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
     }
 
-    res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
+    if (self_kq_mask && self_kq_mask->buffer) {
+        res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
+    }
 
     // swa tensors may not be allocated if there are no SWA attention layers
     if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -615,7 +622,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
       //res &= self_v_idxs_swa->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
     }
 
-    res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
+    if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
+        res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
+    }
 
     return res;
 }

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/src/models/gemma4-assistant.cpp

@@ -39,6 +39,9 @@ void llama_model_gemma4_assistant::load_arch_tensors(llama_model_loader &) {
 
     output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
 
+    create_tensor(tn(LLM_TENSOR_MASKED_EMBD_CENTROIDS, "weight"), {}, TENSOR_NOT_REQUIRED);
+    create_tensor(tn(LLM_TENSOR_MASKED_EMBD_ORDERING),  {}, TENSOR_NOT_REQUIRED);
+
     const int64_t n_embd_backbone = hparams.n_embd_inp();
     nextn_proj_post = create_tensor(tn(LLM_TENSOR_NEXTN_PROJ_POST, "weight"), { n_embd, n_embd_backbone }, 0);
 

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/llama.cpp/tools/server/server-task.cpp

@@ -1393,6 +1393,9 @@ json server_task_result_cmpl_final::to_json_anthropic_stream() {
 //
 void server_task_result_cmpl_partial::update(task_result_state & state) {
     is_updated = true;
+    if (is_begin) {
+        return; // begin marker only flushes headers, skip parsing
+    }
     state.update_chat_msg(content, true, oaicompat_msg_diffs);
 
     // Copy current state for use in to_json_*() (reflects state BEFORE this chunk)

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/src/llama_cpp_bin/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '9563.0.0'
-__version_tuple__ = version_tuple = (9563, 0, 0)
+__version__ = version = '9568.0.0'
+__version_tuple__ = version_tuple = (9568, 0, 0)
 
-__commit_id__ = commit_id = 'gb6c17e417'
+__commit_id__ = commit_id = 'gc6d561ab6'

{llama_cpp_bin-9563.0.0 → llama_cpp_bin-9568.0.0}/src/llama_cpp_bin.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama-cpp-bin
-Version: 9563.0.0
+Version: 9568.0.0
 Summary: llama.cpp server binary built from source
 Author-email: Vladyslav Tkachenko <vladlearns@gmail.com>
 License: AGPL-3.0-or-later