spec : add DFlash support (#22105)
* spec: add DFlash v2 support * dflash: support sliding window attention per layer_types * docs: add dflash section --------- Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
This commit is contained in:
co-authored by
Kashif Rasul
parent
c1a1c8ee94
commit
d1b34251bc
@@ -100,10 +100,10 @@ llama_context::llama_context(
|
||||
cparams.ctx_other = params.ctx_other;
|
||||
}
|
||||
|
||||
if (model.arch == LLM_ARCH_EAGLE3) {
|
||||
if (model.arch == LLM_ARCH_EAGLE3 || model.arch == LLM_ARCH_DFLASH) {
|
||||
if (model.tok_embd == nullptr || model.output == nullptr) {
|
||||
if (params.ctx_other == nullptr) {
|
||||
throw std::runtime_error("EAGLE3 requires ctx_other to be set (this warning is normal during memory fitting)");
|
||||
throw std::runtime_error(model.arch_name() + " requires ctx_other to be set (this warning is normal during memory fitting)");
|
||||
}
|
||||
cparams.ctx_other = params.ctx_other;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user