llama.cpp

Files

T

Georgi GerganovandGitHub d14ce3dab4 llama : MTP clean-up (#23269 )

* llama : disable equal splits for recurrent memory with partial rollback

* spec : re-enable p-min with MTP drafts

* spec : re-enable ngram spec in combination with RS rollback

* spec : fix ngram-map-* params

* spec : fix acceptance logic in combined ngram + draft configs

* graph : fix reuse for combined `token` + `embd` batches

* spec : log parameters for each speculative implementation

- add LOG_INF in each constructor with implementation type and parameters
- extract device string logic into common_speculative_get_devices_str()
- move 'adding speculative implementation' log from init into constructors

Assisted-by: llama.cpp:local pi

* spec : extend --spec-default with ngram-map-k4v

Assisted-by: llama.cpp:local pi

* minor : fix n_embd log

* args : update draft.n_max == 3 + regen docs

* spec : relax ngram-mod rejection thold to 0.25 @ 5 low

* logs : improve

* docs : update speculative decoding CLI argument documentation

- Add missing draft model CPU scheduling and tensor override parameters
- Update --spec-type to include all available types (excluding draft-eagle3 WIP)
- Fix default values to match implementation (n_max=3, n_min=0, p_min=0.0)
- Remove deprecated options (spec-draft-ctx-size, spec-draft-replace)
- Add environment variables for new parameters

Assisted-by: llama.cpp:local pi

* arg : step-back on adding k4v to the default spec config

* cont : fix name

2026-05-19 15:32:58 +03:00

batched-bench

libs : rename libcommon -> libllama-common (#21936 )

2026-04-17 11:11:46 +03:00

cli

llama : MTP clean-up (#23269 )

2026-05-19 15:32:58 +03:00

completion

llama + spec: MTP Support (#22673 )

2026-05-16 20:06:23 +08:00

cvector-generator

libs : rename libcommon -> libllama-common (#21936 )