llama : re-reserve the sched when the nextn extraction flags change (#30020)
The speculative MTP init enables NextN extraction on the target and draft contexts after both were created and their schedulers reserved. With unmasked extraction the trunk graph keeps every token through the last layer instead of cropping to the output rows, so the first decode reallocates to that batch's shape and the next, wider batch trips GGML_SCHED_DEBUG_REALLOC. Invalidate the reserve when the flags change so the next compute re-reserves with the new graph shape. Assisted-by: Claude
This commit is contained in:
1 parent
6753a033f0
commit
1a3011cc0c
1 file changed
+5
@@ -1234,6 +1234,11 @@ void llama_context::set_embeddings(bool value) {
|
||||
void llama_context::set_embeddings_nextn(bool value, bool masked) {
|
||||
LLAMA_LOG_DEBUG("%s: value = %d, masked = %d\n", __func__, value, masked);
|
||||
|
||||
if (cparams.embeddings_nextn != value || cparams.embeddings_nextn_masked != masked) {
|
||||
// these flags change the graph shape
|
||||
sched_need_reserve = true;
|
||||
}
|
||||
|
||||
cparams.embeddings_nextn = value;
|
||||
cparams.embeddings_nextn_masked = masked;
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user