From: Georgi Gerganov <redacted>
Date: Thu, 14 May 2026 08:53:43 +0000 (+0300)
Subject: talk-llama : sync llama.cpp
X-Git-Tag: upstream/1.9.2~400
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=46ca43d6399fdeada1b49fb2126ba373bd9ebc38;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

talk-llama : sync llama.cpp
---

diff --git a/examples/talk-llama/llama-context.cpp b/examples/talk-llama/llama-context.cpp
index 71a59395..3d9714ab 100644
--- a/examples/talk-llama/llama-context.cpp
+++ b/examples/talk-llama/llama-context.cpp
@@ -2475,11 +2475,29 @@ public:
             }
 
             if (need_alloc) {
-                mbuf_cur = std::move(mbuf);
+                if (!mbuf_cur.buf || mbuf_cur.total_size != mbuf.total_size) {
+                    mbuf_cur = std::move(mbuf);
 
-                mbuf_cur.buf.reset(ggml_backend_alloc_ctx_tensors_from_buft(mbuf_cur.ctx.get(), buft));
+                    mbuf_cur.buf.reset(ggml_backend_alloc_ctx_tensors_from_buft(mbuf_cur.ctx.get(), buft));
 
-                LLAMA_LOG_INFO("%s: allocated '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
+                    LLAMA_LOG_INFO("%s: allocated '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
+                } else {
+                    //LLAMA_LOG_INFO("%s: reallocating tensors in '%s' buffer %.3f MiB\n", __func__, ggml_backend_buft_name(buft), mbuf.total_size/1024.0/1024.0);
+
+                    // save the old buffer and allocate the new tensors in it
+                    auto buf = std::move(mbuf_cur.buf);
+
+                    mbuf_cur = std::move(mbuf);
+
+                    ggml_tallocr talloc = ggml_tallocr_new(buf.get());
+
+                    for (size_t i = 0; i < mbuf_cur.org.size(); ++i) {
+                        ggml_backend_view_init(mbuf_cur.org[i]);
+                        ggml_tallocr_alloc(&talloc, mbuf_cur.cpy[i]);
+                    }
+
+                    mbuf_cur.buf = std::move(buf);
+                }
             }
 
             for (size_t i = 0; i < mbuf_cur.org.size(); ++i) {
@@ -2559,8 +2577,7 @@ public:
 
             mbuf.org.push_back(ggml_view_1d(mbuf.ctx.get(), rinfo.tensor, n, rinfo.offset));
 
-            auto & view = mbuf.org.back();
-            view->buffer = rinfo.tensor->buffer;
+            ggml_backend_view_init(mbuf.org.back());
         }
 
         for (auto & [buft, mbuf] : mbufs_new) {
diff --git a/examples/talk-llama/llama.h b/examples/talk-llama/llama.h
index 2ea22672..308e8ba9 100644
--- a/examples/talk-llama/llama.h
+++ b/examples/talk-llama/llama.h
@@ -858,6 +858,8 @@ extern "C" {
                           size_t   n_token_capacity,
                           size_t * n_token_count_out);
 
+#define LLAMA_STATE_SEQ_FLAGS_NONE 0
+
 // for backwards-compat
 #define LLAMA_STATE_SEQ_FLAGS_SWA_ONLY 1