]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
qwen35: use post-norm hidden state for MTP (#24025)
authorAman Gupta <redacted>
Wed, 3 Jun 2026 17:29:09 +0000 (01:29 +0800)
committerGitHub <redacted>
Wed, 3 Jun 2026 17:29:09 +0000 (01:29 +0800)
commit166fe29492abb4093ec889b5c6f6fdb4e3b8ba98
treec3e9d5a61572b1f1d9f36219676dbccf189b5066
parentc8d6a0063613ebd359b0030273746e05658dd605
qwen35: use post-norm hidden state for MTP (#24025)

* qwen35: use post-norm hidden state for MTP

* rename pre_norm to nextn

* fix step35
12 files changed:
common/speculative.cpp
common/speculative.h
src/llama-context.cpp
src/llama-context.h
src/llama-cparams.h
src/llama-ext.h
src/llama-graph.cpp
src/llama-graph.h
src/models/qwen35.cpp
src/models/qwen35moe.cpp
src/models/step35.cpp
tools/server/server-context.cpp