sampling : add support for backend sampling

.github/workflows/build.yml

@@ -1098,6 +1098,7 @@ jobs:
             save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
 
         - name: Build with CMake
+          # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
           run: |
             cmake -S . -B build -G Ninja \
               -DLLAMA_CURL=OFF \
@@ -1107,7 +1108,8 @@ jobs:
               -DCMAKE_CUDA_ARCHITECTURES=89-real \
               -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined \
               -DGGML_NATIVE=OFF \
-              -DGGML_CUDA=ON
+              -DGGML_CUDA=ON \
+              -DGGML_CUDA_CUB_3DOT2=ON
             cmake --build build
 
   windows-2022-cmake-cuda:
@@ -1143,6 +1145,7 @@ jobs:
       - name: Build
         id: cmake_build
         shell: cmd
+        # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
         run: |
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
           cmake -S . -B build -G "Ninja Multi-Config" ^
@@ -1153,7 +1156,8 @@ jobs:
             -DGGML_BACKEND_DL=ON ^
             -DGGML_CPU_ALL_VARIANTS=ON ^
             -DGGML_CUDA=ON ^
-            -DGGML_RPC=ON
+            -DGGML_RPC=ON ^
+            -DGGML_CUDA_CUB_3DOT2=ON
           set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
           cmake --build build --config Release -j %NINJA_JOBS% -t ggml
           cmake --build build --config Release

.github/workflows/release.yml

@@ -420,14 +420,16 @@ jobs:
       - name: Build
         id: cmake_build
         shell: cmd
+        # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
         run: |
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
           cmake -S . -B build -G "Ninja Multi-Config" ^
             -DGGML_BACKEND_DL=ON ^
             -DGGML_NATIVE=OFF ^
             -DGGML_CPU=OFF ^
             -DGGML_CUDA=ON ^
-            -DLLAMA_CURL=OFF
+            -DLLAMA_CURL=OFF ^
+            -DGGML_CUDA_CUB_3DOT2=ON
           set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
           cmake --build build --config Release -j %NINJA_JOBS% --target ggml-cuda
 

.github/workflows/server.yml

@@ -41,6 +41,10 @@ jobs:
         include:
           - build_type: Release
             sanitizer: ""
+            extra_args: ""
+          - build_type: Release
+            sanitizer: ""
+            extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
       fail-fast: false # While -DLLAMA_SANITIZE_THREAD=ON is broken
 
     steps:
@@ -65,6 +69,12 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
 
+      - name: Build
+        id: cmake_build
+        run: |
+          cmake -B build -DLLAMA_CURL=OFF -DLLAMA_BUILD_BORINGSSL=ON
+          cmake --build build --config ${{ matrix.build_type }} -j ${env:NUMBER_OF_PROCESSORS} --target llama-server
+
       - name: Python setup
         id: setup_python
         uses: actions/setup-python@v5
@@ -76,6 +86,14 @@ jobs:
         run: |
           pip install -r tools/server/tests/requirements.txt
 
+      - name: Tests
+        id: server_integration_tests
+        if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) && matrix.build_type == 'Release' }}
+        run: |
+          cd tools/server/tests
+          export ${{ matrix.extra_args }}
+          pytest -v -x -m "not slow"
+
   server-windows:
     runs-on: windows-2022
 

ci/run.sh

@@ -52,7 +52,8 @@ if [ ! -z ${GG_BUILD_METAL} ]; then
 fi
 
 if [ ! -z ${GG_BUILD_CUDA} ]; then
-    CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_CUDA=ON"
+    # TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project
+    CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_CUDA=ON -DGGML_CUDA_CUB_3DOT2=ON"
 
     if command -v nvidia-smi >/dev/null 2>&1; then
         CUDA_ARCH=$(nvidia-smi --query-gpu=compute_cap --format=csv,noheader,nounits 2>/dev/null | head -1 | tr -d '.')

common/arg.cpp

@@ -1695,6 +1695,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             params.sampling.grammar = json_schema_to_grammar(json::parse(schema));
         }
     ).set_sparam());
+    add_opt(common_arg(
+        {"-bs", "--backend-sampling"},
+        "enable backend sampling (experimental) (default: disabled)",
+        [](common_params & params) {
+            params.sampling.backend_sampling = true;
+        }
+    ).set_sparam().set_env("LLAMA_ARG_BACKEND_SAMPLING"));
     add_opt(common_arg(
         {"--pooling"}, "{none,mean,cls,last,rank}",
         "pooling type for embeddings, use model default if unspecified",

common/common.cpp

@@ -1086,6 +1086,7 @@ struct common_init_result::impl {
     std::vector<llama_adapter_lora_ptr> lora;
 
     std::vector<common_sampler_ptr> samplers;
+    std::vector<llama_sampler_seq_config> samplers_seq_config;
 };
 
 common_init_result::common_init_result(common_params & params) :
@@ -1162,10 +1163,19 @@ common_init_result::common_init_result(common_params & params) :
     //    params.sampling.dry_penalty_last_n = llama_n_ctx(lctx);
     //}
 
+    // init the backend samplers as part of the context creation
     pimpl->samplers.resize(cparams.n_seq_max);
+    pimpl->samplers_seq_config.resize(cparams.n_seq_max);
 
     for (int i = 0; i < (int) cparams.n_seq_max; ++i) {
         pimpl->samplers[i].reset(common_sampler_init(model, params.sampling));
+        pimpl->samplers_seq_config[i] = { i, common_sampler_get(pimpl->samplers[i].get()) };
+    }
+
+    // TODO: temporarily gated behind a flag
+    if (params.sampling.backend_sampling) {
+        cparams.samplers   = pimpl->samplers_seq_config.data();
+        cparams.n_samplers = pimpl->samplers_seq_config.size();
     }
 
     llama_context * lctx = llama_init_from_model(model, cparams);
@@ -1189,6 +1199,12 @@ common_sampler * common_init_result::sampler(llama_seq_id seq_id) {
     return pimpl->samplers[seq_id].get();
 }
 
+void common_init_result::reset_samplers() {
+    for (int i = 0; i < (int) pimpl->samplers.size(); ++i) {
+        llama_sampler_reset(common_sampler_get(pimpl->samplers[i].get()));
+    }
+}
+
 std::vector<llama_adapter_lora_ptr> & common_init_result::lora() {
     return pimpl->lora;
 }
@@ -1304,6 +1320,9 @@ common_init_result_ptr common_init_from_params(common_params & params) {
         llama_synchronize(lctx);
         llama_perf_context_reset(lctx);
         llama_set_warmup(lctx, false);
+
+        // reset samplers to reset RNG state after warmup to the seeded state
+        res->reset_samplers();
     }
 
     return res;

common/common.h

@@ -216,6 +216,8 @@ struct common_params_sampling {
     std::vector<llama_logit_bias> logit_bias;     // logit biases to apply
     std::vector<llama_logit_bias> logit_bias_eog; // pre-calculated logit biases for EOG tokens
 
+    bool backend_sampling = false;
+
     bool has_logit_bias() const {
         return !logit_bias.empty();
     }
@@ -689,7 +691,9 @@ struct common_init_result {
 
     llama_model * model();
     llama_context * context();
+
     common_sampler * sampler(llama_seq_id seq_id);
+    void reset_samplers();
 
     std::vector<llama_adapter_lora_ptr> & lora();
 

common/llguidance.cpp

@@ -106,12 +106,16 @@ static void llama_sampler_llg_free(llama_sampler * smpl) {
 }
 
 static llama_sampler_i llama_sampler_llg_i = {
-    /* .name   = */ llama_sampler_llg_name,
-    /* .accept = */ llama_sampler_llg_accept_impl,
-    /* .apply  = */ llama_sampler_llg_apply,
-    /* .reset  = */ llama_sampler_llg_reset,
-    /* .clone  = */ llama_sampler_llg_clone,
-    /* .free   = */ llama_sampler_llg_free,
+    /* .name              = */ llama_sampler_llg_name,
+    /* .accept            = */ llama_sampler_llg_accept_impl,
+    /* .apply             = */ llama_sampler_llg_apply,
+    /* .reset             = */ llama_sampler_llg_reset,
+    /* .clone             = */ llama_sampler_llg_clone,
+    /* .free              = */ llama_sampler_llg_free,
+    /* .backend_init      = */ NULL,
+    /* .backend_accept    = */ NULL,
+    /* .backend_apply     = */ NULL,
+    /* .backend_set_input = */ NULL,
 };
 
 static size_t llama_sampler_llg_tokenize_fn(const void * user_data, const uint8_t * bytes, size_t bytes_len,

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();
@@ -298,6 +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,
@@ -407,6 +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) {

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:

examples/batched/batched.cpp

@@ -68,7 +68,7 @@ int main(int argc, char ** argv) {
     auto sparams = llama_sampler_chain_default_params();
     sparams.no_perf = false;
 
-    std::vector<llama_sampler *> samplers;
+    std::vector<llama_sampler_seq_config> sampler_configs;
 
     for (int32_t i = 0; i < n_parallel; ++i) {
         llama_sampler * smpl = llama_sampler_chain_init(sparams);
@@ -78,7 +78,13 @@ int main(int argc, char ** argv) {
         llama_sampler_chain_add(smpl, llama_sampler_init_temp (params.sampling.temp));
         llama_sampler_chain_add(smpl, llama_sampler_init_dist (params.sampling.seed));
 
-        samplers.push_back(smpl);
+        sampler_configs.push_back({ i, smpl });
+    }
+
+    // TODO: temporarily gated behind a flag
+    if (params.sampling.backend_sampling) {
+        ctx_params.samplers   = sampler_configs.data();
+        ctx_params.n_samplers = sampler_configs.size();
     }
 
     llama_context * ctx = llama_init_from_model(model, ctx_params);
@@ -180,7 +186,7 @@ int main(int argc, char ** argv) {
                 continue;
             }
 
-            const llama_token new_token_id = llama_sampler_sample(samplers[i], ctx, i_batch[i]);
+            const llama_token new_token_id = llama_sampler_sample(sampler_configs[i].sampler, ctx, i_batch[i]);
 
             // is it an end of generation? -> mark the stream as finished
             if (llama_vocab_is_eog(vocab, new_token_id) || n_cur == n_predict) {
@@ -236,15 +242,15 @@ int main(int argc, char ** argv) {
             __func__, n_decode, (t_main_end - t_main_start) / 1000000.0f, n_decode / ((t_main_end - t_main_start) / 1000000.0f));
 
     LOG("\n");
-    llama_perf_sampler_print(samplers[0]);
+    llama_perf_sampler_print(sampler_configs[0].sampler);
     llama_perf_context_print(ctx);
 
     fprintf(stderr, "\n");
 
     llama_batch_free(batch);
 
-    for (auto & sampler_config : samplers) {
-        llama_sampler_free(sampler_config);
+    for (auto & sampler_config : sampler_configs) {
+        llama_sampler_free(sampler_config.sampler);
     }
 
     llama_free(ctx);