@fugood/llama.node 1.4.12 → 1.4.13

package/src/llama.cpp/common/sampling.cpp

@@ -120,17 +120,34 @@ struct common_sampler {
     }
 
     void set_logits(struct llama_context * ctx, int idx) {
-        const auto * logits = llama_get_logits_ith(ctx, idx);
+        const float *       sampled_probs  = llama_get_sampled_probs_ith     (ctx, idx);
+        const float *       sampled_logits = llama_get_sampled_logits_ith    (ctx, idx);
+        const llama_token * sampled_ids    = llama_get_sampled_candidates_ith(ctx, idx);
 
         const llama_model * model = llama_get_model(ctx);
         const llama_vocab * vocab = llama_model_get_vocab(model);
 
         const int n_vocab = llama_vocab_n_tokens(vocab);
 
-        cur.resize(n_vocab);
-
-        for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
-            cur[token_id] = llama_token_data{token_id, logits[token_id], 0.0f};
+        if (sampled_probs) {
+            const uint32_t sampled_probs_count = llama_get_sampled_probs_count_ith(ctx, idx);
+            cur.resize(sampled_probs_count);
+            for (uint32_t i = 0; i < sampled_probs_count; ++i) {
+                cur[i] = llama_token_data{sampled_ids[i], sampled_logits[i], sampled_probs[i]};
+            }
+        } else if (sampled_logits) {
+            const uint32_t sampled_logits_count = llama_get_sampled_logits_count_ith(ctx, idx);
+            cur.resize(sampled_logits_count);
+            for (uint32_t i = 0; i < sampled_logits_count; i++) {
+                cur[i] = llama_token_data{sampled_ids[i], sampled_logits[i], 0.0f};
+            }
+        } else {
+            const auto * logits = llama_get_logits_ith(ctx, idx);
+            GGML_ASSERT(logits != nullptr);
+            cur.resize(n_vocab);
+            for (llama_token token_id = 0; token_id < n_vocab; token_id++) {
+                cur[token_id] = llama_token_data{token_id, logits[token_id], 0.0f};
+            }
         }
 
         cur_p = { cur.data(), cur.size(), -1, false };
@@ -159,7 +176,7 @@ std::string common_params_sampling::print() const {
     return std::string(result);
 }
 
-struct common_sampler * common_sampler_init(const struct llama_model * model, const struct common_params_sampling & params) {
+struct common_sampler * common_sampler_init(const struct llama_model * model, struct common_params_sampling & params) {
     const llama_vocab * vocab = llama_model_get_vocab(model);
 
     llama_sampler_chain_params lparams = llama_sampler_chain_default_params();
@@ -179,24 +196,30 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
 #endif // LLAMA_USE_LLGUIDANCE
     } else {
         std::vector<std::string> trigger_patterns;
-        std::vector<std::string> patterns_anywhere;
         std::vector<llama_token> trigger_tokens;
         for (const auto & trigger : params.grammar_triggers) {
             switch (trigger.type) {
                 case COMMON_GRAMMAR_TRIGGER_TYPE_WORD:
                 {
                     const auto & word = trigger.value;
-                    patterns_anywhere.push_back(regex_escape(word));
+                    trigger_patterns.push_back(regex_escape(word));
                     break;
                 }
                 case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN:
                 {
-                    patterns_anywhere.push_back(trigger.value);
+                    trigger_patterns.push_back(trigger.value);
                     break;
                 }
                 case COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN_FULL:
                 {
-                    trigger_patterns.push_back(trigger.value);
+                    const auto & pattern = trigger.value;
+                    std::string anchored = "^$";
+                    if (!pattern.empty()) {
+                        anchored = (pattern.front() != '^' ? "^" : "")
+                            + pattern
+                            + (pattern.back() != '$' ? "$" : "");
+                    }
+                    trigger_patterns.push_back(anchored);
                     break;
                 }
                 case COMMON_GRAMMAR_TRIGGER_TYPE_TOKEN:
@@ -210,10 +233,6 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
             }
         }
 
-        if (!patterns_anywhere.empty()) {
-            trigger_patterns.push_back("^[\\s\\S]*?(" + string_join(patterns_anywhere, "|") + ")[\\s\\S]*");
-        }
-
         std::vector<const char *> trigger_patterns_c;
         trigger_patterns_c.reserve(trigger_patterns.size());
         for (const auto & regex : trigger_patterns) {
@@ -296,6 +315,12 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, co
         llama_sampler_chain_add(chain, smpl);
     }
 
+    if (grmr && params.backend_sampling) {
+        LOG_WRN("%s: backend sampling is not compatible with grammar, disabling\n", __func__);
+
+        params.backend_sampling = false;
+    }
+
     auto * result = new common_sampler {
         /* .params  = */ params,
         /* .grmr    = */ grmr,
@@ -405,6 +430,25 @@ llama_token common_sampler_sample(struct common_sampler * gsmpl, struct llama_co
     auto & chain = gsmpl->chain;
     auto & cur_p = gsmpl->cur_p; // initialized by set_logits
 
+    // Check if a backend sampler has already sampled a token in which case we
+    // return that token id directly.
+    {
+        id = llama_get_sampled_token_ith(ctx, idx);
+
+        if (id != LLAMA_TOKEN_NULL) {
+            LOG_DBG("%s: Backend sampler selected token: '%d'. Will not run any CPU samplers\n", __func__, id);
+
+            GGML_ASSERT(!gsmpl->grmr && "using grammar in combination with backend sampling is not supported");
+
+            // TODO: simplify
+            gsmpl->cur.resize(1);
+            gsmpl->cur[0] = { id, 0.0f, 1.0f };
+            cur_p = { gsmpl->cur.data(), gsmpl->cur.size(), 0, true };
+
+            return id;
+        }
+    }
+
     gsmpl->set_logits(ctx, idx);
 
     if (grammar_first) {

package/src/llama.cpp/common/sampling.h

@@ -36,7 +36,8 @@ struct common_sampler;
 
 // llama_sampler API overloads
 
-struct common_sampler * common_sampler_init(const struct llama_model * model, const struct common_params_sampling & params);
+// note: can mutate params in some cases
+struct common_sampler * common_sampler_init(const struct llama_model * model, struct common_params_sampling & params);
 
 void common_sampler_free(struct common_sampler * gsmpl);
 
@@ -48,6 +49,7 @@ struct common_sampler * common_sampler_clone (struct common_sampler * gsmpl);
 // arguments can be nullptr to skip printing
 void common_perf_print(const struct llama_context * ctx, const struct common_sampler * gsmpl);
 
+// get the underlying llama_sampler_chain
 struct llama_sampler * common_sampler_get(const struct common_sampler * gsmpl);
 
 // extended sampling implementation:

package/src/llama.cpp/include/llama.h

@@ -316,6 +316,11 @@ extern "C" {
         bool no_alloc;        // only load metadata and simulate memory allocations
     };
 
+    struct llama_sampler_seq_config {
+        llama_seq_id           seq_id;
+        struct llama_sampler * sampler;
+    };
+
     // NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations
     //       https://github.com/ggml-org/llama.cpp/pull/7544
     struct llama_context_params {
@@ -364,6 +369,12 @@ extern "C" {
         bool kv_unified;  // use a unified buffer across the input sequences when computing the attention
                           // try to disable when n_seq_max > 1 for improved performance when the sequences do not share a large prefix
                           // ref: https://github.com/ggml-org/llama.cpp/pull/14363
+
+        // [EXPERIMENTAL]
+        // backend sampler chain configuration (make sure the caller keeps the sampler chains alive)
+        // note: the samplers must be sampler chains (i.e. use llama_sampler_chain_init)
+        struct llama_sampler_seq_config * samplers;
+        size_t                            n_samplers;
     };
 
     // model quantization parameters
@@ -524,6 +535,7 @@ extern "C" {
     LLAMA_API int32_t llama_model_n_ctx_train(const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_embd     (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_embd_inp (const struct llama_model * model);
+    LLAMA_API int32_t llama_model_n_embd_out (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_layer    (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_head     (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_head_kv  (const struct llama_model * model);
@@ -992,6 +1004,32 @@ extern "C" {
     // otherwise: float[n_embd] (1-dimensional)
     LLAMA_API float * llama_get_embeddings_seq(struct llama_context * ctx, llama_seq_id seq_id);
 
+    //
+    // backend sampling API [EXPERIMENTAL]
+    // note: use only if the llama_context was created with at least one llama_sampler_seq_config
+    //
+
+    // Get the backend sampled token for the ith token.
+    // Returns LLAMA_TOKEN_NULL if no token was sampled.
+    LLAMA_API llama_token llama_get_sampled_token_ith(struct llama_context * ctx, int32_t i);
+
+    // Get the backend sampled probabilites for the ith token
+    // The index matches llama_get_sampled_token_ith().
+    // Returns NULL if no probabilites were generated.
+    LLAMA_API float *  llama_get_sampled_probs_ith      (struct llama_context * ctx, int32_t i);
+    LLAMA_API uint32_t llama_get_sampled_probs_count_ith(struct llama_context * ctx, int32_t i);
+
+    // Get the backend sampled logits for the ith token
+    // Returns NULL if no logits were sampled.
+    LLAMA_API float *  llama_get_sampled_logits_ith      (struct llama_context * ctx, int32_t i);
+    LLAMA_API uint32_t llama_get_sampled_logits_count_ith(struct llama_context * ctx, int32_t i);
+
+    // Get the backend sampled candidates (token ids) for the ith token
+    // These are needed to map probability/logit indices to vocab token ids.
+    // Returns NULL if no candidates were sampled.
+    LLAMA_API llama_token * llama_get_sampled_candidates_ith      (struct llama_context * ctx, int32_t i);
+    LLAMA_API uint32_t      llama_get_sampled_candidates_count_ith(struct llama_context * ctx, int32_t i);
+
     //
     // Vocab
     //
@@ -1163,11 +1201,16 @@ extern "C" {
     //
     //    llama_sampler_free(smpl);
     //
-    // TODO: In the future, llama_sampler will be utilized to offload the sampling to the backends (e.g. GPU).
-    //
 
     typedef void * llama_sampler_context_t;
 
+    struct llama_sampler_data {
+        struct ggml_tensor * logits;
+        struct ggml_tensor * probs;
+        struct ggml_tensor * sampled;
+        struct ggml_tensor * candidates;
+    };
+
     // user code can implement the interface below in order to create custom llama_sampler
     struct llama_sampler_i {
         const char *           (*name)  (const struct llama_sampler * smpl);                                 // can be NULL
@@ -1177,17 +1220,45 @@ extern "C" {
         struct llama_sampler * (*clone) (const struct llama_sampler * smpl);                                 // can be NULL if ctx is NULL
         void                   (*free)  (      struct llama_sampler * smpl);                                 // can be NULL if ctx is NULL
 
-        // TODO: API for internal libllama usage for appending the sampling to an existing ggml_cgraph
-        //void (*apply_ggml) (struct llama_sampler * smpl, ...);
+        // [EXPERIMENTAL]
+        // backend sampling interface:
+
+        // return true if the backend supports all ops needed by the sampler
+        // note: call once per sampler
+        bool (*backend_init)(struct llama_sampler * smpl, ggml_backend_buffer_type_t buft);
+
+        // call after .backend_apply()
+        void (*backend_accept)(
+                struct llama_sampler * smpl,
+                struct ggml_context  * ctx,
+                struct ggml_cgraph   * gf,
+                struct ggml_tensor   * selected_token);
+
+        // call after .backend_init()
+        void (*backend_apply)(
+                struct llama_sampler      * smpl,
+                struct ggml_context       * ctx,
+                struct ggml_cgraph        * gf,
+                struct llama_sampler_data * data);
+
+        // called before graph execution to set inputs for the current ubatch
+        void (*backend_set_input)(struct llama_sampler * smpl);
     };
 
     struct llama_sampler {
-        const struct llama_sampler_i * iface;
-        llama_sampler_context_t        ctx;
+        struct llama_sampler_i * iface;
+
+        llama_sampler_context_t ctx;
     };
 
+    // [EXPERIMENTAL]
+    // attach a sampler to the context
+    // note: prefer initializing the context with llama_context_params.samplers when possible
+    // note: changing the samplers of a context can cause graph reallocations and degraded performance
+    LLAMA_API bool llama_set_sampler(struct llama_context * ctx, llama_seq_id seq_id, struct llama_sampler * smpl);
+
     // mirror of llama_sampler_i:
-    LLAMA_API struct llama_sampler * llama_sampler_init  (const struct llama_sampler_i * iface, llama_sampler_context_t ctx);
+    LLAMA_API struct llama_sampler * llama_sampler_init  (      struct llama_sampler_i * iface, llama_sampler_context_t ctx);
     LLAMA_API const char *           llama_sampler_name  (const struct llama_sampler * smpl);
     LLAMA_API void                   llama_sampler_accept(      struct llama_sampler * smpl, llama_token token);
     LLAMA_API void                   llama_sampler_apply (      struct llama_sampler * smpl, llama_token_data_array * cur_p);
@@ -1203,7 +1274,15 @@ extern "C" {
 
     // important: takes ownership of the sampler object and will free it when llama_sampler_free is called
     LLAMA_API void                   llama_sampler_chain_add(      struct llama_sampler * chain, struct llama_sampler * smpl);
-    LLAMA_API struct llama_sampler * llama_sampler_chain_get(const struct llama_sampler * chain, int32_t i);
+
+    // return NULL if:
+    //   - the sampler is NULL
+    //   - the sampler is not a llama_sampler_chain
+    //   - the index is out of bounds, unless i == -1
+    //   - if i == -1, returns the chain itself (can be used to check if the sampler is a chain)
+    LLAMA_API struct llama_sampler * llama_sampler_chain_get(      struct llama_sampler * chain, int32_t i);
+
+    // the total number of samplers in the chain
     LLAMA_API int                    llama_sampler_chain_n  (const struct llama_sampler * chain);
 
     // after removing a sampler, the chain will no longer own it, and it will not be freed when the chain is freed

package/src/llama.cpp/src/llama-arch.cpp

@@ -152,6 +152,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
     { LLM_KV_VOCAB_SIZE,                        "%s.vocab_size"                        },
     { LLM_KV_CONTEXT_LENGTH,                    "%s.context_length"                    },
     { LLM_KV_EMBEDDING_LENGTH,                  "%s.embedding_length"                  },
+    { LLM_KV_EMBEDDING_LENGTH_OUT,              "%s.embedding_length_out"              },
     { LLM_KV_FEATURES_LENGTH,                   "%s.features_length"                   },
     { LLM_KV_BLOCK_COUNT,                       "%s.block_count"                       },
     { LLM_KV_LEADING_DENSE_BLOCK_COUNT,         "%s.leading_dense_block_count"         },
@@ -2075,6 +2076,7 @@ static std::set<llm_tensor> llm_get_tensor_names(llm_arch arch) {
                 LLM_TENSOR_TOKEN_EMBD,
                 LLM_TENSOR_OUTPUT_NORM_LFM2,
                 LLM_TENSOR_OUTPUT,
+                LLM_TENSOR_DENSE_2_OUT,
             };
         case LLM_ARCH_LFM2MOE:
             return {

package/src/llama.cpp/src/llama-arch.h

@@ -156,6 +156,7 @@ enum llm_kv {
     LLM_KV_VOCAB_SIZE,
     LLM_KV_CONTEXT_LENGTH,
     LLM_KV_EMBEDDING_LENGTH,
+    LLM_KV_EMBEDDING_LENGTH_OUT,
     LLM_KV_FEATURES_LENGTH,
     LLM_KV_BLOCK_COUNT,
     LLM_KV_LEADING_DENSE_BLOCK_COUNT,