model: support vllm decision 2 model (#30378)
* models: support pplx-decider * vllm d2 * update * clarify naming rule * stricter validation * fix ci * rm redundant filter_tensors
This commit is contained in:
1 parent
ccdbe29053
commit
097cf33d94
23 files changed
+549
-19
No files matched your search
@@ -3604,6 +3604,11 @@ private:
|
||||
n_past = std::min(n_past, slot.task->n_tokens_shared);
|
||||
}
|
||||
|
||||
// the outputs of a decision are read from the batch, so its first position must be evaluated
|
||||
if (n_decision_first >= 0) {
|
||||
n_past = std::min(n_past, n_decision_first);
|
||||
}
|
||||
|
||||
// if there is an alora invoked, don't cache after the invocation start
|
||||
if (slot.alora_invocation_start > 0) {
|
||||
SLT_DBG(slot, "only caching to alora invocation start (n_past = %d, alora_invocation_start = %d)\n", n_past, slot.alora_invocation_start);
|
||||
|
||||
Reference in new issue
Block a user