Commit 21fa9c043 for llama.cpp

commit 21fa9c043f0e4f574b36cd06cff4b4bce64ec76f
Author: Titaniumtown <titaniumtown@proton.me>
Date:   Mon Nov 16 01:52:09 2026 -0800

    kv-cells: avoid an O(n_cells) scan per sequence removal (#32380)

diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp
index 3d6fd2a5f..5dd0e5f02 100644
--- a/src/llama-kv-cache.cpp
+++ b/src/llama-kv-cache.cpp
@@ -458,19 +458,7 @@ bool llama_kv_cache::seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos p1) {
         auto & cells = v_cells[seq_to_stream[seq_id]];
         auto & head  = v_heads[seq_to_stream[seq_id]];

-        uint32_t new_head = cells.size();
-
-        for (uint32_t i = 0; i < cells.size(); ++i) {
-            if (!cells.pos_in(i, p0, p1)) {
-                continue;
-            }
-
-            if (cells.seq_has(i, seq_id) && cells.seq_rm(i, seq_id)) {
-                if (new_head == cells.size()) {
-                    new_head = i;
-                }
-            }
-        }
+        const uint32_t new_head = cells.seq_rm(seq_id, p0, p1);

         // If we freed up a slot, set head to it so searching can start there.
         if (new_head != cells.size() && new_head < head) {
diff --git a/src/llama-kv-cells.h b/src/llama-kv-cells.h
index b0202cb28..1187cc736 100644
--- a/src/llama-kv-cells.h
+++ b/src/llama-kv-cells.h
@@ -308,6 +308,27 @@ public:
         return false;
     }

+    // remove seq_id from its cells at positions in [p0, p1)
+    // return the lowest index of a cell that becomes empty, or size() if none does
+    uint32_t seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos p1) {
+        assert(seq_id >= 0);
+        assert(seq_id < LLAMA_MAX_SEQ);
+
+        uint32_t res = size();
+
+        const auto & sp = seq_pos[seq_id];
+        for (auto it = sp.lower_bound({ p0, 0 }); it != sp.end() && it->first < p1; ) {
+            const uint32_t i = it->second;
+            ++it; // advance first: seq_rm(i, seq_id) erases this entry from sp
+
+            if (seq_rm(i, seq_id)) {
+                res = std::min(res, i);
+            }
+        }
+
+        return res;
+    }
+
     // return true if the cell becomes empty (i.e. it did not contain seq_id before the call)
     bool seq_keep(uint32_t i, llama_seq_id seq_id) {
         assert(i < pos.size());
diff --git a/tests/test-kv-cache.cpp b/tests/test-kv-cache.cpp
index c8255f572..4b48387b9 100644
--- a/tests/test-kv-cache.cpp
+++ b/tests/test-kv-cache.cpp
@@ -3,6 +3,7 @@

 #include <numeric>
 #include <string>
+#include <vector>

 static void init_model(llama_model & model, uint32_t n_layer) {
     model.hparams = {};
@@ -105,6 +106,75 @@ int main() {
         }
     }

+    // seq_rm removes [p0, p1) of one sequence, a negative bound is open
+    {
+        std::unique_ptr<llama_model> model(llama_model_create(LLM_ARCH_LLAMA, llama_model_default_params()));
+        init_model(*model, 1);
+
+        llama_kv_cache kv(*model, false, model->hparams, GGML_TYPE_F16, GGML_TYPE_F16,
+                false, false, true, 32, 2, 0, LLAMA_SWA_TYPE_NONE, nullptr, nullptr, nullptr, nullptr);
+
+        // returns the first cell that takes the tokens
+        auto add = [&](llama_seq_id seq_id, llama_pos p0, uint32_t n) {
+            std::vector<llama_token>    token(n, 1);
+            std::vector<llama_pos>      pos(n);
+            std::vector<int32_t>        n_seq_id(n, 1);
+            std::vector<llama_seq_id *> seq_ids(n, &seq_id);
+            std::iota(pos.begin(), pos.end(), p0);
+
+            llama_ubatch ubatch = {};
+            ubatch.n_tokens     = n;
+            ubatch.n_seq_tokens = n;
+            ubatch.n_seqs       = 1;
+            ubatch.n_seqs_unq   = 1;
+            ubatch.n_pos        = 1;
+            ubatch.token        = token.data();
+            ubatch.pos          = pos.data();
+            ubatch.n_seq_id     = n_seq_id.data();
+            ubatch.seq_id       = seq_ids.data();
+            ubatch.seq_id_unq   = &seq_id;
+
+            const auto sinfo = kv.find_slot(ubatch, false);
+            GGML_ASSERT(!sinfo.empty());
+            kv.apply_ubatch(sinfo, ubatch);
+
+            return sinfo.head();
+        };
+
+        GGML_ASSERT(add(0, 0, 8) == 0);
+        GGML_ASSERT(add(1, 0, 4) == 8);
+
+        // the tail of sequence 0, the other sequence keeps its cells
+        GGML_ASSERT(kv.seq_rm(0, 5, -1));
+        GGML_ASSERT(kv.seq_pos_min(0) == 0 && kv.seq_pos_max(0) == 4);
+        GGML_ASSERT(kv.seq_pos_min(1) == 0 && kv.seq_pos_max(1) == 3);
+
+        // the next tokens go to the lowest freed cell
+        GGML_ASSERT(add(0, 5, 2) == 5);
+
+        // p1 is not part of the range
+        GGML_ASSERT(kv.seq_rm(0, -1, 2));
+        GGML_ASSERT(kv.seq_pos_min(0) == 2 && kv.seq_pos_max(0) == 6);
+        GGML_ASSERT(kv.seq_rm(0, 6, 6));
+        GGML_ASSERT(kv.seq_pos_max(0) == 6);
+
+        // freed cells are taken in cell order, so a higher position can sit in a lower cell
+        GGML_ASSERT(add(0, 7, 3) == 0);
+        GGML_ASSERT(kv.seq_rm(0, 6, -1));
+        GGML_ASSERT(add(0, 6, 1) == 0);
+
+        // a cell shared with another sequence stays for that sequence
+        kv.seq_cp(0, 1, 5, -1);
+        GGML_ASSERT(kv.seq_rm(0, 5, -1));
+        GGML_ASSERT(kv.seq_pos_max(0) == 4 && kv.seq_pos_max(1) == 6);
+
+        // every cell of a repeated position is removed
+        add(0, 5, 1);
+        add(0, 5, 1);
+        GGML_ASSERT(kv.seq_rm(0, 5, 6));
+        GGML_ASSERT(kv.seq_pos_max(0) == 4);
+    }
+
     llama_backend_free();
     return 0;
 }