talk-llama : sync llama.cpp

examples/talk-llama/llama-context.cpp

@@ -1,5 +1,6 @@
 #include "llama-context.h"
 
+#include "ggml.h"
 #include "llama-arch.h"
 #include "llama-impl.h"
 #include "llama-batch.h"
@@ -8,6 +9,7 @@
 #include "llama-mmap.h"
 #include "llama-model.h"
 #include "llama-ext.h"
+#include "llama.h"
 
 #include <cinttypes>
 #include <cmath>
@@ -217,10 +219,10 @@ llama_context::llama_context(
 
     if (!hparams.vocab_only) {
         // GPU backends
-        for (auto * dev : model.devices) {
-            ggml_backend_t backend = ggml_backend_dev_init(dev, nullptr);
+        for (const auto & dev : model.devices) {
+            ggml_backend_t backend = ggml_backend_dev_init(dev.dev, nullptr);
             if (backend == nullptr) {
-                throw std::runtime_error(format("failed to initialize %s backend", ggml_backend_dev_name(dev)));
+                throw std::runtime_error(format("failed to initialize %s backend", ggml_backend_dev_name(dev.dev)));
             }
             backends.emplace_back(backend);
         }
@@ -295,8 +297,8 @@ llama_context::llama_context(
 
             if (backend_type == GGML_BACKEND_DEVICE_TYPE_CPU && !model.devices.empty()) {
                 // use the host buffer of the first device CPU for faster transfer of the intermediate state
-                auto * dev = model.devices[0];
-                auto * host_buft = ggml_backend_dev_host_buffer_type(dev);
+                const auto & dev = model.devices[0];
+                auto * host_buft = ggml_backend_dev_host_buffer_type(dev.dev);
                 if (host_buft) {
                     buft = host_buft;
                 }
@@ -342,14 +344,6 @@ llama_context::llama_context(
 
         if (cparams.pipeline_parallel) {
             LLAMA_LOG_INFO("%s: pipeline parallelism enabled\n", __func__);
-
-            if (!graph_reuse_disable) {
-                // TODO: figure out a way to make graph reuse work with pipeline parallelism
-                // ref: https://github.com/ggml-org/llama.cpp/pull/20463
-                LLAMA_LOG_WARN("%s: graph reuse is currently not compatible with pipeline parallelism - disabling\n", __func__);
-
-                graph_reuse_disable = true;
-            }
         }
 
         sched_reserve();
@@ -594,7 +588,7 @@ 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());
         //
@@ -1028,9 +1022,11 @@ void llama_context::set_abort_callback(bool (*abort_callback)(void * data), void
 
     for (auto & backend : backends) {
         auto * reg = ggml_backend_dev_backend_reg(ggml_backend_get_device(backend.get()));
-        auto * set_abort_callback_fn = (ggml_backend_set_abort_callback_t) ggml_backend_reg_get_proc_address(reg, "ggml_backend_set_abort_callback");
-        if (set_abort_callback_fn) {
-            set_abort_callback_fn(backend.get(), this->abort_callback, this->abort_callback_data);
+        if (reg) {
+            auto * set_abort_callback_fn = (ggml_backend_set_abort_callback_t) ggml_backend_reg_get_proc_address(reg, "ggml_backend_set_abort_callback");
+            if (set_abort_callback_fn) {
+                set_abort_callback_fn(backend.get(), this->abort_callback, this->abort_callback_data);
+            }
         }
     }
 }
@@ -1165,9 +1161,11 @@ bool llama_context::set_adapter_cvec(
                 int32_t   il_end) {
     LLAMA_LOG_DEBUG("%s: il_start = %d, il_end = %d\n", __func__, il_start, il_end);
 
-    // TODO: should we reserve?
+    bool res = cvec->apply(model, data, len, n_embd, il_start, il_end);
 
-    return cvec->apply(model, data, len, n_embd, il_start, il_end);
+    sched_need_reserve = true;
+
+    return res;
 }
 
 llm_graph_result * llama_context::process_ubatch(const llama_ubatch & ubatch, llm_graph_type gtype, llama_memory_context_i * mctx, ggml_status & ret) {
@@ -1187,6 +1185,13 @@ llm_graph_result * llama_context::process_ubatch(const llama_ubatch & ubatch, ll
     if (!graph_reuse_disable && res->can_reuse(gparams)) {
         //LLAMA_LOG_DEBUG("%s: reusing previous graph\n", __func__);
 
+        // with pipeline parallelism, the previous graph_compute_async may still be running
+        // on the GPU. we must synchronize before set_inputs to avoid overwriting input tensors
+        // that the previous compute is still reading.
+        if (cparams.pipeline_parallel) {
+            ggml_backend_sched_synchronize(sched.get());
+        }
+
         n_reused++;
     } else {
         res->reset();
@@ -1345,8 +1350,11 @@ int llama_context::encode(const llama_batch & batch_inp) {
                         const llama_seq_id seq_id  = ubatch.seq_id_unq[s];
                         const int32_t      seq_idx = ubatch.seq_idx[seq_id];
 
-                        embd_seq_out[seq_id].resize(n_embd);
-                        ggml_backend_tensor_get_async(backend_embd, t_embd, embd_seq_out[seq_id].data(), (n_embd*seq_idx)*sizeof(float), n_embd*sizeof(float));
+                        // use n_embd_out (not n_embd_inp) - the pooled embedding has the model's
+                        // output dimension, which differs from input dimension for deepstack models (e.g. qwen3vl)
+                        const uint32_t n_embd_out = hparams.n_embd_out();
+                        embd_seq_out[seq_id].resize(n_embd_out);
+                        ggml_backend_tensor_get_async(backend_embd, t_embd, embd_seq_out[seq_id].data(), (n_embd_out*seq_idx)*sizeof(float), n_embd_out*sizeof(float));
                     }
                 } break;
             case LLAMA_POOLING_TYPE_RANK:
@@ -1767,12 +1775,16 @@ int llama_context::decode(const llama_batch & batch_inp) {
                         // extract sequence embeddings (cleared before processing each batch)
                         auto & embd_seq_out = embd_seq;
 
+                        // use n_embd_out (not n_embd_inp) - the pooled embedding has the model's
+                        // output dimension, which differs from input dimension for deepstack models (e.g. qwen3vl)
+                        const uint32_t n_embd_out = hparams.n_embd_out();
+
                         for (uint32_t s = 0; s < ubatch.n_seqs_unq; ++s) {
                             const llama_seq_id seq_id  = ubatch.seq_id_unq[s];
                             const int32_t      seq_idx = ubatch.seq_idx[seq_id];
 
-                            embd_seq_out[seq_id].resize(n_embd);
-                            ggml_backend_tensor_get_async(backend_embd, t_embd, embd_seq_out[seq_id].data(), (n_embd*seq_idx)*sizeof(float), n_embd*sizeof(float));
+                            embd_seq_out[seq_id].resize(n_embd_out);
+                            ggml_backend_tensor_get_async(backend_embd, t_embd, embd_seq_out[seq_id].data(), (n_embd_out*seq_idx)*sizeof(float), n_embd_out*sizeof(float));
                         }
                     } break;
                 case LLAMA_POOLING_TYPE_RANK:
@@ -1944,6 +1956,7 @@ uint32_t llama_context::output_reserve(int32_t n_outputs) {
             LLAMA_LOG_ERROR("%s: failed to allocate output buffer of size %.2f MiB\n", __func__, new_size / (1024.0 * 1024.0));
             return 0;
         }
+        ggml_backend_buffer_clear(buf_output.get(), 0);
     }
 
     float * output_base = (float *) ggml_backend_buffer_get_base(buf_output.get());
@@ -2623,7 +2636,7 @@ void llama_context::perf_reset() {
     n_reused    = 0;
 }
 
-std::map<ggml_backend_buffer_type_t, llama_memory_breakdown_data> llama_context::memory_breakdown() const {
+llama_memory_breakdown llama_context::memory_breakdown() const {
     std::map<ggml_backend_buffer_type_t, llama_memory_breakdown_data> ret;
     for (const auto & [buft, size] : model.memory_breakdown()) {
         ret[buft].model += size;
@@ -2933,7 +2946,22 @@ llama_context * llama_init_from_model(
         params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_DISABLED;
     }
 
-    if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO && ggml_is_quantized(params.type_k)) {
+    if (model->split_mode() == LLAMA_SPLIT_MODE_TENSOR) {
+        if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO) {
+            LLAMA_LOG_INFO("%s: enabling flash_attn since it is required for SPLIT_MODE_TENSOR\n", __func__);
+            params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED;
+        }
+        if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_ENABLED) {
+            LLAMA_LOG_ERROR("%s: SPLIT_MODE_TENSOR requires flash_attn to be enabled\n", __func__);
+            return nullptr;
+        }
+        if (ggml_is_quantized(params.type_k) || ggml_is_quantized(params.type_v)) {
+            LLAMA_LOG_ERROR("%s: simultaneous use of SPLIT_MODE_TENSOR and KV cache quantization not implemented\n", __func__);
+            return nullptr;
+        }
+    }
+
+    if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) {
         const uint32_t blck_size = ggml_blck_size(params.type_k);
         for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
             if (model->hparams.n_embd_head_k(il) % blck_size != 0) {
@@ -2944,7 +2972,7 @@ llama_context * llama_init_from_model(
         }
     }
 
-    if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO && ggml_is_quantized(params.type_v)) {
+    if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_v)) {
         const uint32_t blck_size = ggml_blck_size(params.type_v);
         for (uint32_t il = 0; il < model->hparams.n_layer; ++il) {
             if (model->hparams.n_embd_head_v(il) % blck_size != 0) {
@@ -3465,142 +3493,6 @@ void llama_perf_context_reset(llama_context * ctx) {
     ctx->perf_reset();
 }
 
-void llama_memory_breakdown_print(const struct llama_context * ctx) {
-    const std::vector<ggml_backend_dev_t> & devices = ctx->get_model().devices;
-
-    std::map<ggml_backend_buffer_type_t, llama_memory_breakdown_data> memory_breakdown = ctx->memory_breakdown();
-
-    std::vector<std::array<std::string, 9>> table_data;
-    table_data.reserve(devices.size());
-    const std::string template_header = "%s: | %s | %s   %s    %s   %s   %s   %s    %s |\n";
-    const std::string template_gpu    = "%s: | %s | %s = %s + (%s = %s + %s + %s) + %s |\n";
-    const std::string template_other  = "%s: | %s | %s   %s    %s = %s + %s + %s    %s |\n";
-
-    table_data.push_back({template_header, "memory breakdown [MiB]", "total", "free", "self", "model", "context", "compute", "unaccounted"});
-
-    constexpr size_t MiB = 1024 * 1024;
-    const std::vector<std::string> desc_prefixes_strip = {"NVIDIA ", "GeForce ", "Tesla ", "AMD ", "Radeon ", "Instinct "};
-
-    // track seen buffer types to avoid double counting:
-    std::set<ggml_backend_buffer_type_t> seen_buffer_types;
-
-    // accumulative memory breakdown for each device and for host:
-    std::vector<llama_memory_breakdown_data> mb_dev(devices.size());
-    llama_memory_breakdown_data              mb_host;
-
-    for (const auto & buft_mb : memory_breakdown) {
-        ggml_backend_buffer_type_t          buft = buft_mb.first;
-        const llama_memory_breakdown_data & mb   = buft_mb.second;
-        if (ggml_backend_buft_is_host(buft)) {
-            mb_host.model   += mb.model;
-            mb_host.context += mb.context;
-            mb_host.compute += mb.compute;
-            seen_buffer_types.insert(buft);
-            continue;
-        }
-        ggml_backend_dev_t dev = ggml_backend_buft_get_device(buft);
-        if (dev) {
-            int i_dev = -1;
-            for (size_t i = 0; i < devices.size(); i++) {
-                if (devices[i] == dev) {
-                    i_dev = i;
-                    break;
-                }
-            }
-            if (i_dev != -1) {
-                mb_dev[i_dev].model   += mb.model;
-                mb_dev[i_dev].context += mb.context;
-                mb_dev[i_dev].compute += mb.compute;
-                seen_buffer_types.insert(buft);
-                continue;
-            }
-        }
-    }
-
-    // print memory breakdown for each device:
-    for (size_t i = 0; i < devices.size(); i++) {
-        ggml_backend_dev_t          dev = devices[i];
-        llama_memory_breakdown_data mb  = mb_dev[i];
-
-        const std::string name = ggml_backend_dev_name(dev);
-        std::string desc = ggml_backend_dev_description(dev);
-        for (const std::string & prefix : desc_prefixes_strip) {
-            if (desc.length() >= prefix.length() && desc.substr(0, prefix.length()) == prefix) {
-                desc = desc.substr(prefix.length());
-            }
-        }
-
-        size_t free, total;
-        ggml_backend_dev_memory(dev, &free, &total);
-
-        const size_t self = mb.model + mb.context + mb.compute;
-        const size_t unaccounted = total - self - free;
-
-        table_data.push_back({
-            template_gpu,
-            "  - " + name + " (" + desc + ")",
-            std::to_string(total / MiB),
-            std::to_string(free / MiB),
-            std::to_string(self / MiB),
-            std::to_string(mb.model / MiB),
-            std::to_string(mb.context / MiB),
-            std::to_string(mb.compute / MiB),
-            std::to_string(unaccounted / MiB)});
-    }
-
-    // print memory breakdown for host:
-    {
-        const size_t self = mb_host.model + mb_host.context + mb_host.compute;
-        table_data.push_back({
-            template_other,
-            "  - Host",
-            "", // total
-            "", // free
-            std::to_string(self / MiB),
-            std::to_string(mb_host.model / MiB),
-            std::to_string(mb_host.context / MiB),
-            std::to_string(mb_host.compute / MiB),
-            ""}); // unaccounted
-    }
-
-    // print memory breakdown for all remaining buffer types:
-    for (const auto & buft_mb : memory_breakdown) {
-        ggml_backend_buffer_type_t          buft = buft_mb.first;
-        const llama_memory_breakdown_data & mb   = buft_mb.second;
-        if (seen_buffer_types.count(buft) == 1) {
-            continue;
-        }
-        const std::string name = ggml_backend_buft_name(buft);
-        const size_t self = mb.model + mb.context + mb.compute;
-        table_data.push_back({
-            template_other,
-            "  - " + name,
-            "", // total
-            "", // free
-            std::to_string(self / MiB),
-            std::to_string(mb.model / MiB),
-            std::to_string(mb.context / MiB),
-            std::to_string(mb.compute / MiB),
-            ""}); // unaccounted
-        seen_buffer_types.insert(buft);
-    }
-
-    for (size_t j = 1; j < table_data[0].size(); j++) {
-        size_t max_len = 0;
-        for (const auto & td : table_data) {
-            max_len = std::max(max_len, td[j].length());
-        }
-        for (auto & td : table_data) {
-            td[j].insert(j == 1 ? td[j].length() : 0, max_len - td[j].length(), ' ');
-        }
-    }
-    for (const auto & td : table_data) {
-        LLAMA_LOG_INFO(td[0].c_str(),
-            __func__, td[1].c_str(), td[2].c_str(), td[3].c_str(), td[4].c_str(), td[5].c_str(),
-            td[6].c_str(), td[7].c_str(), td[8].c_str());
-    }
-}
-
 //
 // training
 //
@@ -3631,3 +3523,11 @@ void llama_opt_epoch(
         callback_train,
         callback_eval);
 }
+
+//
+// ext
+//
+
+llama_memory_breakdown llama_get_memory_breakdown(const struct llama_context * ctx) {
+    return ctx->memory_breakdown();
+}