llama : support multi-output backend sampling (#25532)

* Enable backend sampling with token speculation

* Clamp the mask sum before converting it into the sampled index

* Add a numeric context parameter declaring the maximum outputs one sequence

* More fixes

* Don't reuse memory for output views.

* Match dist between CPU and GPU

* Fix CPU and backend sampling mismatches

* Simpify some of the changes

* Fix tests on Vulkan

* More test fixes

* Rebase changes

* Rebase and address review comments

* Address review comments

* Address review comments

* Update src/llama-sampler.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

common/common.cpp

@@ -1639,6 +1639,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
     cparams.n_seq_max         = params.n_parallel;
     cparams.n_rs_seq          = params.speculative.need_n_rs_seq();
     cparams.n_outputs_max     = std::max(params.n_outputs_max, 0);
+    cparams.n_outputs_max_per_seq = std::max(params.n_outputs_max_per_seq, 0);
     cparams.n_batch           = params.n_batch;
     cparams.n_ubatch          = params.n_ubatch;
     cparams.n_threads         = params.cpuparams.n_threads;

common/common.h

@@ -447,6 +447,7 @@ struct common_params {
     int32_t n_parallel            =     1; // number of parallel sequences to decode
     int32_t n_sequences           =     1; // number of sequences to decode
     int32_t n_outputs_max         =     0; // max outputs in a batch (0 = n_batch)
+    int32_t n_outputs_max_per_seq =     1; // max outputs per sequence
     int32_t grp_attn_n            =     1; // group-attention factor
     int32_t grp_attn_w            =   512; // group-attention width
     int32_t n_print               =    -1; // print token count every n tokens (-1 = disabled)

common/llguidance.cpp

@@ -116,6 +116,8 @@ static llama_sampler_i llama_sampler_llg_i = {
     /* .backend_accept    = */ NULL,
     /* .backend_apply     = */ NULL,
     /* .backend_set_input = */ NULL,
+    /* .backend_reset     = */ NULL,
+    /* .copy_state        = */ NULL,
 };
 
 static size_t llama_sampler_llg_tokenize_fn(const void * user_data, const uint8_t * bytes, size_t bytes_len,

common/reasoning-budget.cpp

@@ -217,6 +217,8 @@ static struct llama_sampler_i common_reasoning_budget_i = {
     /* .backend_accept    = */ nullptr,
     /* .backend_apply     = */ nullptr,
     /* .backend_set_input = */ nullptr,
+    /* .backend_reset     = */ nullptr,
+    /* .copy_state        = */ nullptr,
 };
 
 static struct llama_sampler * common_reasoning_budget_clone(const struct llama_sampler * smpl) {

common/sampling.cpp

@@ -518,6 +518,26 @@ struct common_sampler * common_sampler_clone(common_sampler * gsmpl) {
     };
 }
 
+void common_sampler_copy(const common_sampler * src, common_sampler * dst) {
+    if (!src || !dst || src == dst) {
+        return;
+    }
+
+    GGML_ASSERT((src->grmr == nullptr) == (dst->grmr == nullptr));
+    GGML_ASSERT((src->rbudget == nullptr) == (dst->rbudget == nullptr));
+
+    llama_sampler_copy(src->grmr,    dst->grmr);
+    llama_sampler_copy(src->rbudget, dst->rbudget);
+    llama_sampler_copy(src->chain,   dst->chain);
+
+    dst->params     = src->params;
+    dst->prev       = src->prev;
+    dst->cur        = src->cur;
+    dst->cur_p      = src->cur_p;
+    dst->cur_p.data = src->cur_p.data ? dst->cur.data() : nullptr; // re-point to dst's buffer
+    dst->t_total_us = src->t_total_us;
+}
+
 void common_perf_print(const struct llama_context * ctx, const struct common_sampler * gsmpl) {
     // TODO: measure grammar performance
 

common/sampling.h

@@ -47,6 +47,7 @@ void common_sampler_free(struct common_sampler * gsmpl);
 void                    common_sampler_accept(struct common_sampler * gsmpl, llama_token token, bool is_generated);
 void                    common_sampler_reset (struct common_sampler * gsmpl);
 struct common_sampler * common_sampler_clone (struct common_sampler * gsmpl);
+void                    common_sampler_copy  (const struct common_sampler * src, struct common_sampler * dst);
 
 // arguments can be nullptr to skip printing
 void common_perf_print(const struct llama_context * ctx, const struct common_sampler * gsmpl);

common/speculative.cpp

@@ -2299,6 +2299,7 @@ common_params common_base_params_to_speculative(const common_params & params) {
     result.cache_type_k  = params_spec.cache_type_k;
     result.cache_type_v  = params_spec.cache_type_v;
     result.n_outputs_max = params.n_parallel;
+    result.n_outputs_max_per_seq = 1;
 
     return result;
 }
@@ -2384,6 +2385,17 @@ common_speculative_init_result_ptr common_speculative_init_from_params(common_pa
     return std::make_unique<common_speculative_init_result>(params, model_tgt, ctx_tgt);
 }
 
+common_speculative_output_limits common_speculative_get_output_limits(
+        int32_t n_batch, int32_t n_parallel, int32_t n_draft) {
+    const int64_t per_seq = 1 + (int64_t) std::max(0, n_draft);
+    const int64_t total   = (int64_t) n_parallel * per_seq;
+
+    return {
+        /* .total   = */ (int32_t) std::min<int64_t>(n_batch, total),
+        /* .per_seq = */ (int32_t) std::min<int64_t>(n_batch, per_seq),
+    };
+}
+
 // initialization of the speculative decoding system
 //
 common_speculative * common_speculative_init(common_params_speculative & params, uint32_t n_seq) {

common/speculative.h

@@ -25,6 +25,15 @@ int32_t common_speculative_n_max(const common_params_speculative * spec);
 
 common_params common_base_params_to_speculative(const common_params & params);
 
+struct common_speculative_output_limits {
+    int32_t total;
+    int32_t per_seq;
+};
+
+// return the output limits needed for speculative decoding
+common_speculative_output_limits common_speculative_get_output_limits(
+        int32_t n_batch, int32_t n_parallel, int32_t n_draft);
+
 common_speculative * common_speculative_init(common_params_speculative & params, uint32_t n_seq);
 
 void common_speculative_free(common_speculative * spec);