upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

spec: support eagle3 for qwen3.5 & 3.6 (#24593)

Browse Source 
* spec: support qwen3.5 & 3.6 eagle3 draft

* eagle3: Add deferred boundary checkpoints restore support for hybrid models

* apply suggestions

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* spec: adapt to API change

* spec: fix naming

* cont : add TODO

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ruixiang Wang
2026-06-19 12:08:50 +02:00
committed by GitHub
parent 159d093a43
commit b14e3fb90c
7 changed files with 92 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/server-context.cpp
View File

@@ -2172,6 +2172,8 @@ private:
cur.update_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
cur.update_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
// stash the draft's speculative state with the checkpoint
common_speculative_get_state(spec.get(), slot.id, cur.data_spec);
SLT_INF(slot,
"created context checkpoint %d of %d (pos_min = %d, pos_max = %d, n_tokens = %" PRId64 ", size = %.3f MiB)\n",
@@ -2998,6 +3000,8 @@ private:
// restore the context checkpoint
it->load_tgt(ctx_tgt, slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
it->load_dft(ctx_dft.get(), slot.id, LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY);
// restore the draft's speculative state
common_speculative_set_state(spec.get(), slot.id, it->data_spec);
pos_next = std::min(pos_next, std::max(it->pos_min + 1, it->pos_max));
n_past = std::min(slot.prompt.tokens.size_up_to_pos(pos_next), (size_t) it->n_tokens);