Merge pull request #490 from janhq/update-dev-from-master-2026-04-19-01-00

Sync master with upstream release b8840

Author: jan-service-account

.github/workflows/release.yml

@@ -687,6 +687,11 @@ jobs:
         with:
           fetch-depth: 0
 
+      - name: Free up disk space
+        uses: ggml-org/free-disk-space@v1.3.1
+        with:
+          tool-cache: true
+
       - name: ccache
         uses: ggml-org/ccache-action@v1.2.21
         with:

convert_hf_to_gguf.py

@@ -10912,14 +10912,14 @@ def set_vocab(self):
         vocab_size = -(vocab_size // -pad_vocab) * pad_vocab
         self.hparams["vocab_size"] = vocab_size
 
-        assert max(tokenizer.vocab.values()) < vocab_size
+        assert max(tokenizer.vocab.values()) < vocab_size  # ty: ignore[unresolved-attribute]
 
         tokpre = self.get_vocab_base_pre(tokenizer)
 
-        reverse_vocab = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}
-        added_vocab = tokenizer.get_added_vocab()
+        reverse_vocab = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}  # ty: ignore[unresolved-attribute]
+        added_vocab = tokenizer.get_added_vocab()  # ty: ignore[unresolved-attribute]
 
-        added_tokens_decoder = tokenizer.added_tokens_decoder
+        added_tokens_decoder = tokenizer.added_tokens_decoder  # ty: ignore[unresolved-attribute]
 
         for i in range(vocab_size):
             if i not in reverse_vocab:
@@ -10930,7 +10930,7 @@ def set_vocab(self):
                 if token in added_vocab:
                     if not added_tokens_decoder[i].normalized:
                         previous_token = token
-                        token = tokenizer.decode(tokenizer.encode(token, add_special_tokens=False))
+                        token = tokenizer.decode(tokenizer.encode(token, add_special_tokens=False))  # ty: ignore[unresolved-attribute, invalid-assignment]
                         if previous_token != token:
                             logger.info(f"{repr(previous_token)} is encoded and decoded back to {repr(token)} using AutoTokenizer")
 

examples/llama.android/lib/src/main/cpp/CMakeLists.txt

@@ -51,6 +51,6 @@ target_include_directories(${CMAKE_PROJECT_NAME} PRIVATE
 
 target_link_libraries(${CMAKE_PROJECT_NAME}
         llama
-        common
+        llama-common
         android
         log)

ggml/src/ggml-backend-meta.cpp

@@ -1270,7 +1270,45 @@ static void ggml_backend_meta_buffer_get_tensor(ggml_backend_buffer_t buffer, co
     GGML_ASSERT(ggml_is_contiguous(tensor));
 
     const ggml_backend_meta_split_state split_state = ggml_backend_meta_get_split_state(tensor, /*assume_sync =*/ false);
-    GGML_ASSERT(split_state.n_segments == 1);
+
+    if (split_state.n_segments != 1) {
+        GGML_ASSERT(split_state.axis >= 0 && split_state.axis < GGML_MAX_DIMS);
+        GGML_ASSERT(offset == 0);
+        GGML_ASSERT(size == ggml_nbytes(tensor));
+        GGML_ASSERT(tensor->ne[3] == 1);
+        size_t offset_data = 0;
+        std::vector<size_t> simple_offsets(n_bufs, 0);
+        if (split_state.axis == GGML_BACKEND_SPLIT_AXIS_0) {
+            GGML_ASSERT(tensor->ne[2] == 1);
+            const int64_t blck_size = ggml_blck_size(tensor->type);
+            for (size_t s = 0; s < split_state.n_segments; s++) {
+                for (size_t j = 0; j < n_bufs; j++) {
+                    const ggml_tensor * simple_tensor = ggml_backend_meta_buffer_simple_tensor(tensor, j);
+                    GGML_ASSERT(split_state.ne[s*n_bufs + j] % blck_size == 0);
+                    const size_t nbytes = split_state.ne[s*n_bufs + j]/blck_size * tensor->nb[0];
+                    ggml_backend_tensor_get_2d(simple_tensor, (char *) data + offset_data, simple_offsets[j], nbytes,
+                        tensor->ne[1], simple_tensor->nb[1], tensor->nb[1]);
+                    offset_data       += nbytes;
+                    simple_offsets[j] += nbytes;
+                }
+            }
+            GGML_ASSERT(offset_data*tensor->ne[1] == size);
+            return;
+        }
+        GGML_ASSERT(split_state.axis == GGML_BACKEND_SPLIT_AXIS_1);
+        for (size_t s = 0; s < split_state.n_segments; s++) {
+            for (size_t j = 0; j < n_bufs; j++) {
+                const ggml_tensor * simple_tensor = ggml_backend_meta_buffer_simple_tensor(tensor, j);
+                const size_t nbytes = split_state.ne[s*n_bufs + j] * tensor->nb[1];
+                ggml_backend_tensor_get_2d(simple_tensor, (char *) data + offset_data, simple_offsets[j], nbytes,
+                    tensor->ne[2], simple_tensor->nb[2], tensor->nb[2]);
+                offset_data       += nbytes;
+                simple_offsets[j] += nbytes;
+            }
+        }
+        GGML_ASSERT(offset_data*tensor->ne[2] == size);
+        return;
+    }
 
     switch (split_state.axis) {
         case GGML_BACKEND_SPLIT_AXIS_0:

src/llama-graph.cpp

@@ -1077,9 +1077,9 @@ llm_graph_qkv llm_graph_context::build_qkv(
         // fused QKV path
         ggml_tensor * qkv = build_lora_mm(layer.wqkv, cur, layer.wqkv_s);
         cb(qkv, "wqkv", il);
-        if (layer.bqkv) {
-            qkv = ggml_add(ctx0, qkv, layer.bqkv);
-            cb(qkv, "bqkv", il);
+        if (layer.wqkv_b) {
+            qkv = ggml_add(ctx0, qkv, layer.wqkv_b);
+            cb(qkv, "wqkv_b", il);
         }
         if (hparams.f_clamp_kqv > 0.0f) {
             qkv = ggml_clamp(ctx0, qkv, -hparams.f_clamp_kqv, hparams.f_clamp_kqv);
@@ -1097,8 +1097,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
         // separate Q/K/V path
         Qcur = build_lora_mm(layer.wq, cur, layer.wq_s);
         cb(Qcur, "Qcur", il);
-        if (layer.bq) {
-            Qcur = ggml_add(ctx0, Qcur, layer.bq);
+        if (layer.wq_b) {
+            Qcur = ggml_add(ctx0, Qcur, layer.wq_b);
             cb(Qcur, "Qcur", il);
         }
         if (hparams.f_clamp_kqv > 0.0f) {
@@ -1107,8 +1107,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
         }
         Kcur = build_lora_mm(layer.wk, cur, layer.wk_s);
         cb(Kcur, "Kcur", il);
-        if (layer.bk) {
-            Kcur = ggml_add(ctx0, Kcur, layer.bk);
+        if (layer.wk_b) {
+            Kcur = ggml_add(ctx0, Kcur, layer.wk_b);
             cb(Kcur, "Kcur", il);
         }
         if (hparams.f_clamp_kqv > 0.0f) {
@@ -1117,8 +1117,8 @@ llm_graph_qkv llm_graph_context::build_qkv(
         }
         Vcur = build_lora_mm(layer.wv, cur, layer.wv_s);
         cb(Vcur, "Vcur", il);
-        if (layer.bv) {
-            Vcur = ggml_add(ctx0, Vcur, layer.bv);
+        if (layer.wv_b) {
+            Vcur = ggml_add(ctx0, Vcur, layer.wv_b);
             cb(Vcur, "Vcur", il);
         }
         if (hparams.f_clamp_kqv > 0.0f) {