kv-cache : use ggml_set_rows

[ggerganov]

depends #14274

Utilize ggml_set_rows() for updating the KV cache.

• Make the graph static with respect to the KV cells head offset
• Relax the requirement for continuous KV slots of the input ubatch, making the defrag logic almost obsolete

Currently enabled only if the environment variable LLAMA_SET_ROWS is defined. If not, we fallback to the original way of updating the KV cache using a view + cpy of continuous slots. This is needed until the ggml_set_rows() implementation is finalized and supported by all backends.

Will merge after #14274.

Testing

# regular
LLAMA_SET_ROWS=1 ./bin/llama-cli -m ../models/llama-3.2-3b-instruct/ggml-model-q8_0.gguf \
     -p "I believe the meaning of life is" -n 32 --top-k 1 -fa

# SWA
LLAMA_SET_ROWS=1 ./bin/llama-cli -m ../models/gemma-3-4b/ggml-model-q8_0.gguf \
     -p "I believe the meaning of life is" -n 32 --top-k 1 -fa

Next PRs

• Introduce the concept of "virtual sequences"
• Extend llama_kv_cache_unified to support virtual sequences
• Extend the attention graph to support virtual sequences
• Enable efficient multi-sequence decoding

[rgerganov]

I tried this PR with the following change in the RPC backend:

diff --git a/ggml/src/ggml-rpc/ggml-rpc.cpp b/ggml/src/ggml-rpc/ggml-rpc.cpp
index f468f796..dcbede89 100644
--- a/ggml/src/ggml-rpc/ggml-rpc.cpp
+++ b/ggml/src/ggml-rpc/ggml-rpc.cpp
@@ -761,6 +761,8 @@ static enum ggml_status ggml_backend_rpc_graph_compute(ggml_backend_t backend, g
     ggml_backend_rpc_context * rpc_ctx = (ggml_backend_rpc_context *)backend->context;
     std::vector<uint8_t> input;
     serialize_graph(cgraph, input);
+    auto graph_hash = fnv_hash(input.data(), input.size());
+    printf("RPC graph compute: hash = 0x%" PRIx64 ", size = %zu\n", graph_hash, input.size());
     rpc_msg_graph_compute_rsp response;
     auto sock = get_socket(rpc_ctx->endpoint);
     bool status = send_rpc_cmd(sock, RPC_CMD_GRAPH_COMPUTE, input.data(), input.size(), &response, sizeof(response));

The compute graph doesn't change and produces the same hash with gpt2, tinyllama and mistral-7b models. However, the hash does change with gemma3 models. The serialized graph includes tensor addresses, so it's possible that we rebuild same tensors on different addresses resulting in different graph hash.

But in any way this looks like a great progress!

[ggerganov]

However, the hash does change with gemma3 models.

Yes, this is expected. I've applied the change only for the unified cache. For the unified+iswa, it is still using the ggml_cpy:

https://github.com/ggml-org/llama.cpp/pull/14285/files#diff-9be9eea14f4aefce7375482c05968900192634e88e92ac263cedb955a64ad7feR1290-R1291

[ggerganov]

Should work with Gemma now as well.

[ggerganov]

The non-FA path is now also supported, though I am not 100% sure this is the best way to do it.

[ggerganov]

The non-FA path is now also supported, though I am not 100% sure this is the best way to do it.

I don't observe any performance regression with CPU-only build, so the implementation should be good enough I think.