vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 16:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

note: smartcache is broken for rnn currently

Browse source
This commit is contained in:
Concedo 2026-03-15 11:31:47 +08:00
commit f3d2f58fa8
30 changed files with 2232 additions and 875 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/llama-context.cpp
View file

@ -521,7 +521,12 @@ void llama_context::sched_reserve() {
if (cparams.fused_gdn_ch) {
// more than one token in the batch per sequence in order to take the chunked path
auto * gf = graph_reserve(16*n_seqs, n_seqs, n_outputs, mctx.get(), true);
// note: n_outputs must match n_tokens for embedding models with mean/rank pooling,
// because build_pooling creates inp_mean with shape [n_tokens, n_seqs] and multiplies
// it with t_embd which is reduced to [n_outputs, ...] via out_ids. if n_outputs != n_tokens,
// the ggml_mul_mat assertion fails. this matches the pp reservation below (line ~553).
const uint32_t n_tokens_ch = 16*n_seqs;
auto * gf = graph_reserve(n_tokens_ch, n_seqs, n_tokens_ch, mctx.get(), true);
if (!gf) {
throw std::runtime_error("failed to reserve graph for fused Gated Delta Net check (chunked)");
}