cui-llama.rn 1.7.3 → 1.7.6

package/ios/rnllama.xcframework/ios-arm64/rnllama.framework/Headers/llama-memory-recurrent.h

@@ -0,0 +1,183 @@
+#pragma once
+
+#include "llama-batch.h"
+#include "llama-graph.h"
+#include "llama-memory.h"
+
+#include <set>
+#include <vector>
+
+//
+// llama_memory_recurrent
+//
+
+// TODO: extract the cache state used for graph computation into llama_memory_recurrent_context_i
+//       see the implementation of llama_kv_cache_unified_context_i for an example how to do it
+class llama_memory_recurrent : public llama_memory_i {
+public:
+
+    // this callback is used to filter out layers that should not be included in the cache
+    using layer_filter_cb = std::function<bool(int32_t il)>;
+
+    llama_memory_recurrent(
+            const llama_model &  model,
+              layer_filter_cb && filter,
+                    lm_ggml_type    type_r,
+                    lm_ggml_type    type_s,
+                         bool    offload,
+                     uint32_t    mem_size,
+                     uint32_t    n_seq_max);
+
+    ~llama_memory_recurrent() = default;
+
+    //
+    // llama_memory_i
+    //
+
+    llama_memory_context_ptr init_batch(
+            llama_batch_allocr & balloc,
+            uint32_t n_ubatch,
+            bool embd_all) override;
+
+    llama_memory_context_ptr init_full() override;
+
+    llama_memory_context_ptr init_update(llama_context * lctx, bool optimize) override;
+
+    void clear(bool data) override;
+
+    bool seq_rm  (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1) override;
+    void seq_cp  (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) override;
+    void seq_keep(llama_seq_id seq_id)                                                          override;
+    void seq_add (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, llama_pos shift) override;
+    void seq_div (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, int d) override;
+
+    llama_pos seq_pos_min(llama_seq_id seq_id) const override;
+    llama_pos seq_pos_max(llama_seq_id seq_id) const override;
+
+    bool prepare(const std::vector<llama_ubatch> & ubatches);
+
+    // find a contiguous slot of memory cells and emplace the ubatch there
+    bool find_slot(const llama_ubatch & ubatch);
+
+    bool get_can_shift() const override;
+
+    // state write/load
+
+    void state_write(llama_io_write_i & io, llama_seq_id seq_id = -1) const override;
+    void state_read (llama_io_read_i  & io, llama_seq_id seq_id = -1) override;
+
+    uint32_t head = 0; // the location where the batch will be placed in the cache (see find_slot())
+    uint32_t size = 0; // total number of cells, shared across all sequences
+    uint32_t used = 0; // used cells (i.e. at least one seq_id)
+
+    // computed before each graph build
+    uint32_t n = 0;
+
+    // first zero-ed state
+    int32_t rs_z = -1;
+
+    // TODO: optimize for recurrent state needs
+    struct mem_cell {
+        llama_pos pos  = -1;
+        int32_t   src  = -1; // used to know where states should be copied from
+        int32_t   src0 = -1; // like src, but only used when setting the inputs (allowing to copy once)
+        int32_t   tail = -1;
+
+        std::set<llama_seq_id> seq_id;
+
+        bool has_seq_id(const llama_seq_id & id) const {
+            return seq_id.find(id) != seq_id.end();
+        }
+
+        bool is_empty() const {
+            return seq_id.empty();
+        }
+
+        bool is_same_seq(const mem_cell & other) const {
+            return seq_id == other.seq_id;
+        }
+    };
+
+    std::vector<mem_cell> cells;
+
+    // per layer
+    std::vector<lm_ggml_tensor *> r_l;
+    std::vector<lm_ggml_tensor *> s_l;
+
+private:
+    //const llama_model & model;
+    const llama_hparams & hparams;
+
+    const uint32_t n_seq_max = 1;
+
+    std::vector<lm_ggml_context_ptr>        ctxs;
+    std::vector<lm_ggml_backend_buffer_ptr> bufs;
+
+    size_t total_size() const;
+
+    size_t size_r_bytes() const;
+    size_t size_s_bytes() const;
+
+    void state_write_meta(llama_io_write_i & io, const std::vector<std::pair<uint32_t, uint32_t>> & cell_ranges, llama_seq_id seq_id = -1) const;
+    void state_write_data(llama_io_write_i & io, const std::vector<std::pair<uint32_t, uint32_t>> & cell_ranges) const;
+
+    bool state_read_meta(llama_io_read_i & io, uint32_t cell_count, llama_seq_id dest_seq_id = -1);
+    bool state_read_data(llama_io_read_i & io, uint32_t cell_count);
+};
+
+class llama_memory_recurrent_context : public llama_memory_context_i {
+public:
+    // used for errors
+    llama_memory_recurrent_context(llama_memory_status status);
+
+    // used to create a full-cache or update context
+    llama_memory_recurrent_context(
+            llama_memory_recurrent * mem);
+
+    // used to create a batch processing context from a batch
+    llama_memory_recurrent_context(
+            llama_memory_recurrent * mem,
+            std::vector<llama_ubatch> ubatches);
+
+    virtual ~llama_memory_recurrent_context();
+
+    //
+    // llama_memory_context_i
+    //
+
+    bool next()  override;
+    bool apply() override;
+
+    llama_memory_status  get_status() const override;
+    const llama_ubatch & get_ubatch() const override;
+
+    //
+    // llama_memory_recurrent_context specific API
+    //
+
+    uint32_t get_n_rs() const;
+    uint32_t get_head() const;
+    int32_t  get_rs_z() const;
+    uint32_t get_size() const;
+
+    lm_ggml_tensor * get_r_l(int32_t il) const;
+    lm_ggml_tensor * get_s_l(int32_t il) const;
+
+    int32_t s_copy(int i) const;
+
+private:
+    const llama_memory_status status;
+
+    llama_memory_recurrent * mem;
+
+    size_t i_next = 0;
+
+    std::vector<llama_ubatch> ubatches;
+
+    //
+    // data needed for building the compute graph for the current ubatch:
+    // TODO: extract all the state like `head` and `n` here
+    //
+
+    const bool is_full = false;
+};

package/ios/rnllama.xcframework/ios-arm64/rnllama.framework/Headers/llama-memory.h

@@ -2,6 +2,15 @@
 
 #include "llama.h"
 
+#include <memory>
+
+struct llama_ubatch;
+
+class llama_batch_allocr;
+
+class llama_io_write_i;
+class llama_io_read_i;
+
 struct llama_memory_params {
     // kv cache
     lm_ggml_type type_k;
@@ -11,22 +20,94 @@ struct llama_memory_params {
     bool swa_full;
 };
 
+enum llama_memory_status {
+    LLAMA_MEMORY_STATUS_SUCCESS = 0,
+    LLAMA_MEMORY_STATUS_NO_UPDATE,
+    LLAMA_MEMORY_STATUS_FAILED_PREPARE,
+    LLAMA_MEMORY_STATUS_FAILED_COMPUTE,
+};
+
+// helper function for combining the status of two memory contexts
+// useful for implementing hybrid memory types (e.g. iSWA)
+llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1);
+
+// the interface for managing the memory context during batch processing
+// this interface is implemented per memory type. see:
+//   - llama_kv_cache_unified_context
+//   - llama_kv_cache_unified_iswa_context
+//   ...
+//
+// the only method that should mutate the memory and the memory context is llama_memory_i::apply()
+struct llama_memory_context_i {
+    virtual ~llama_memory_context_i() = default;
+
+    // consume the current ubatch from the context and proceed to the next one
+    // return false if we are done
+    virtual bool next() = 0;
+
+    // apply the memory state for the current ubatch to the memory object
+    // return false on failure
+    virtual bool apply() = 0;
+
+    // get the current ubatch
+    virtual const llama_ubatch & get_ubatch() const = 0;
+
+    // get the status of the memory context - used for error handling and checking if any updates would be applied
+    virtual llama_memory_status get_status() const = 0;
+};
+
+using llama_memory_context_ptr = std::unique_ptr<llama_memory_context_i>;
+
 // general concept of LLM memory
 // the KV cache is a type of LLM memory, but there can be other types
-class llama_memory_i {
-public:
+struct llama_memory_i {
     virtual ~llama_memory_i() = default;
 
-    virtual void clear() = 0;
+    // split the input batch into a set of ubatches and verify that they can fit into the cache
+    // return a context object containing the ubatches and memory state required to process them
+    // check the llama_memory_context_i::get_status() for the result
+    virtual llama_memory_context_ptr init_batch(
+            llama_batch_allocr & balloc,
+            uint32_t n_ubatch,
+            bool embd_all) = 0;
+
+    // simulate full cache, used for allocating worst-case compute buffers
+    virtual llama_memory_context_ptr init_full() = 0;
+
+    // prepare for any pending memory updates, such as shifts, defrags, etc.
+    // status == LLAMA_MEMORY_STATUS_NO_UPDATE if there is nothing to update
+    virtual llama_memory_context_ptr init_update(llama_context * lctx, bool optimize) = 0;
+
+    // getters
+    virtual bool get_can_shift() const = 0;
+
+    //
+    // ops
+    //
+
+    // if data == true, the data buffers will also be cleared together with the metadata
+    virtual void clear(bool data) = 0;
 
     virtual bool seq_rm  (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1) = 0;
     virtual void seq_cp  (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) = 0;
     virtual void seq_keep(llama_seq_id seq_id) = 0;
-    virtual void seq_add (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, llama_pos delta) = 0;
+    virtual void seq_add (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, llama_pos shift) = 0;
     virtual void seq_div (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, int d) = 0;
 
     virtual llama_pos seq_pos_min(llama_seq_id seq_id) const = 0;
     virtual llama_pos seq_pos_max(llama_seq_id seq_id) const = 0;
 
-    virtual bool get_can_edit() const = 0;
+    //
+    // state write/read
+    //
+
+    virtual void state_write(llama_io_write_i & io, llama_seq_id seq_id = -1) const = 0;
+    virtual void state_read (llama_io_read_i  & io, llama_seq_id seq_id = -1) = 0;
+};
+
+using llama_memory_ptr = std::unique_ptr<llama_memory_i>;
+
+// TODO: temporary until the llama_kv_cache is removed from the public API
+struct llama_kv_cache : public llama_memory_i {
+    virtual ~llama_kv_cache() = default;
 };

package/ios/rnllama.xcframework/ios-arm64/rnllama.framework/Headers/llama-model.h

@@ -73,6 +73,7 @@ enum llm_type {
     LLM_TYPE_40B,
     LLM_TYPE_65B,
     LLM_TYPE_70B,
+    LLM_TYPE_142B,
     LLM_TYPE_236B,
     LLM_TYPE_290B,
     LLM_TYPE_314B,
@@ -94,6 +95,8 @@ enum llm_type {
     LLM_TYPE_17B_128E, // llama4 Maverick
     LLM_TYPE_30B_A3B,
     LLM_TYPE_235B_A22B,
+    LLM_TYPE_E2B,
+    LLM_TYPE_E4B,
 };
 
 std::string llama_rope_scaling_type_name(llama_rope_scaling_type rope_scaling_type);
@@ -315,6 +318,19 @@ struct llama_layer {
     struct lm_ggml_tensor * ffn_up_scale   = nullptr;
     struct lm_ggml_tensor * ffn_down_scale = nullptr;
 
+    // altup & laurel
+    struct lm_ggml_tensor * per_layer_inp_gate   = nullptr;
+    struct lm_ggml_tensor * per_layer_proj       = nullptr;
+    struct lm_ggml_tensor * per_layer_post_norm  = nullptr;
+    struct lm_ggml_tensor * altup_correct_coef   = nullptr;
+    struct lm_ggml_tensor * altup_correct_scale  = nullptr;
+    struct lm_ggml_tensor * altup_predict_coef   = nullptr;
+    struct lm_ggml_tensor * altup_router         = nullptr;
+    struct lm_ggml_tensor * altup_router_norm    = nullptr;
+    struct lm_ggml_tensor * laurel_l             = nullptr;
+    struct lm_ggml_tensor * laurel_r             = nullptr;
+    struct lm_ggml_tensor * laurel_post_norm     = nullptr;
+
     struct llama_layer_posnet posnet;
 
     struct llama_layer_convnext convnext;
@@ -329,6 +345,9 @@ struct llama_model {
     llama_hparams hparams = {};
     llama_vocab   vocab;
 
+    // for classifier models
+    std::vector<std::string> classifier_labels;
+
     struct lm_ggml_tensor * tok_embd   = nullptr;
     struct lm_ggml_tensor * type_embd  = nullptr;
     struct lm_ggml_tensor * pos_embd   = nullptr;
@@ -350,6 +369,13 @@ struct llama_model {
     struct lm_ggml_tensor * conv1d   = nullptr;
     struct lm_ggml_tensor * conv1d_b = nullptr;
 
+    // gemma3n altup
+    struct lm_ggml_tensor * tok_embd_per_layer   = nullptr;
+    struct lm_ggml_tensor * altup_proj           = nullptr;
+    struct lm_ggml_tensor * altup_unembd_proj    = nullptr;
+    struct lm_ggml_tensor * per_layer_model_proj = nullptr;
+    struct lm_ggml_tensor * per_layer_proj_norm  = nullptr;
+
     std::vector<llama_layer> layers;
 
     llama_model_params params;

package/ios/rnllama.xcframework/ios-arm64/rnllama.framework/Headers/llama-vocab.h

@@ -74,6 +74,7 @@ struct llama_vocab {
     bool get_add_space_prefix          () const;
     bool get_add_bos                   () const;
     bool get_add_eos                   () const;
+    bool get_add_sep                   () const;
     bool get_ignore_merges             () const;
     bool get_clean_spaces              () const;
     bool get_remove_extra_whitespaces  () const;