Open source / #18830
Open source
ggml-org/llama.cpp b10731
GitHub Releases · github-actions[bot] · 2 months ago
<details open> qwen4exp: support recurrent state rollback (#28123) MTP speculative decoding needs the target state to move back by the number of rejected draft tokens. Without rollback support the context is classified as SEQ_RM_TYPE_FULL and the server serializes the whole recu…
Source and ranking details
- Source adapter
- github-releases
- Source weight
- 3
- Points
- 0
- Age
- 1508.6 h
- Stored score
- 0.00000
- Current score
- 0.00000
- First seen
- 2026-09-01T08:37:06.014Z
Newsletter
Get practical AI engineering notes
Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.