fix: correct misspellings in code comments (#21217)

- emdeddings → embeddings (gemma3.cpp, gemma3n-iswa.cpp,
gemma-embedding.cpp)
- imlpemented → implemented (llama-adapter.cpp)
- interere → interfere (llama-graph.cpp)
- overridde → overridden (chat.cpp)
- stastistics → statistics (ngram-map.h)
- layed → laid (llama-kv-cache.h)
- worster → worst (llama-context.cpp)
- sequantial → sequential (llama-batch.h)

Author: lainon1

common/chat.cpp

@@ -221,7 +221,7 @@ using chat_template_caps = jinja::caps;
 struct common_chat_templates {
     bool add_bos;
     bool add_eos;
-    bool has_explicit_template;  // Model had builtin template or template overridde was specified.
+    bool has_explicit_template;  // Model had builtin template or template overridden was specified.
     std::unique_ptr<common_chat_template> template_default;  // always set (defaults to chatml)
     std::unique_ptr<common_chat_template> template_tool_use;
 };

common/ngram-map.h

@@ -51,7 +51,7 @@ struct common_ngram_map_value {
 // statistics of a n-gram
 struct common_ngram_map_key {
     size_t   key_idx;   // index of key n-gram in token-history
-    size_t   stat_idx;  // index of last token of stastistics computation (key_num, values)
+    size_t   stat_idx;  // index of last token of statistics computation (key_num, values)
 
     uint16_t key_num;   // number of occurrences of this key n-gram in token-history
     common_ngram_map_value values[COMMON_NGRAM_MAX_VALUES]; // some known values after the key

src/llama-adapter.cpp

@@ -294,7 +294,7 @@ static void llama_adapter_lora_init_impl(llama_model & model, const char * path_
     }
 
     // get extra buffer types of the CPU
-    // TODO: a more general solution for non-CPU extra buft should be imlpemented in the future
+    // TODO: a more general solution for non-CPU extra buft should be implemented in the future
     //       ref: https://github.com/ggml-org/llama.cpp/pull/12593#pullrequestreview-2718659948
     std::vector<ggml_backend_buffer_type_t> buft_extra;
     {

src/llama-batch.h

@@ -18,7 +18,7 @@ struct llama_ubatch {
     }
 
     // typical for M-RoPE cases:
-    //   0 - sequantial position of the tokens/embeddings in the sequence
+    //   0 - sequential position of the tokens/embeddings in the sequence
     //   1 - y position in the image
     //   2 - x position in the image
     //   3 - other

src/llama-context.cpp

@@ -586,7 +586,7 @@ void llama_context::sched_reserve() {
 
     // reserve again with pp graph to avoid ggml-alloc reallocations during inference
     {
-        // TODO: not sure if the following graph would be worster case for multi-stream KV caches:
+        // TODO: not sure if the following graph would be worst case for multi-stream KV caches:
         //
         // auto * gf = graph_reserve(n_tokens, 1, n_tokens, mctx.get());
         //

src/llama-graph.cpp

@@ -1665,7 +1665,7 @@ ggml_tensor * llm_graph_context::build_inp_attn_scale() const {
 
 ggml_tensor * llm_graph_context::build_inp_out_ids() const {
     // note: when all tokens are output, we could skip this optimization to spare the ggml_get_rows() calls,
-    //       but this would make the graph topology depend on the number of output tokens, which can interere with
+    //       but this would make the graph topology depend on the number of output tokens, which can interfere with
     //       features that require constant topology such as pipeline parallelism
     //       ref: https://github.com/ggml-org/llama.cpp/pull/14275#issuecomment-2987424471
     //if (n_outputs < n_tokens) {

src/llama-kv-cache.h

@@ -333,7 +333,7 @@ class llama_kv_cache_context : public llama_memory_context_i {
     ggml_tensor * get_v(ggml_context * ctx, int32_t il) const;
 
     // store k_cur and v_cur in the cache based on the provided head location
-    // note: the heads in k_cur and v_cur should be layed out contiguously in memory
+    // note: the heads in k_cur and v_cur should be laid out contiguously in memory
     //   - k_cur  [n_embd_head_k, n_head_k, n_tokens]
     //   - k_idxs [n_tokens]
     //   - v_cur  [n_embd_head_v, n_head_v, n_tokens]

src/models/gemma-embedding.cpp

@@ -9,7 +9,7 @@ llm_build_gemma_embedding::llm_build_gemma_embedding(const llama_model & model,
 
     inpL = build_inp_embd(model.tok_embd);
 
-    // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings)
+    // important: do not normalize weights for raw embeddings input (i.e. encoded image embeddings)
     inpL = ggml_scale(ctx0, inpL, ubatch.token ? sqrtf(n_embd) : 1.0f);
     cb(inpL, "inp_scaled", -1);
 

src/models/gemma3.cpp

@@ -9,7 +9,7 @@ llm_build_gemma3<iswa>::llm_build_gemma3(const llama_model & model, const llm_gr
 
     inpL = build_inp_embd(model.tok_embd);
 
-    // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings)
+    // important: do not normalize weights for raw embeddings input (i.e. encoded image embeddings)
     inpL = ggml_scale(ctx0, inpL, ubatch.token ? sqrtf(n_embd) : 1.0f);
     cb(inpL, "inp_scaled", -1);
 

src/models/gemma3n-iswa.cpp

@@ -12,7 +12,7 @@ llm_build_gemma3n_iswa::llm_build_gemma3n_iswa(const llama_model & model, const
 
     inpL = build_inp_embd(model.tok_embd);
 
-    // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings)
+    // important: do not normalize weights for raw embeddings input (i.e. encoded image embeddings)
     inpL = ggml_scale(ctx0, inpL, ubatch.token ? sqrtf(n_embd) : 1.0f);
     cb(inpL, "inp_scaled", -1);