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

..

jinja

common : fix jinja warnings with clang 21 (#22313)

2026-04-24 12:36:02 +02:00

arg.cpp

llama : MTP clean-up (#23269)

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

arg.h

mtmd, server, common: expose modalities to /v1/models (#22952)

2026-05-12 19:08:07 +02:00

base64.hpp

llava : expose as a shared library for downstream projects (#3613)

2023-11-07 00:36:23 +03:00

build-info.cpp.in

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

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

build-info.h

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

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

chat-auto-parser-generator.cpp

common : delegate assistant continuation to underlying template handlers (#23089)

2026-05-17 13:36:05 +02:00

chat-auto-parser-helpers.cpp

common : replace wrap_for_generation with a prefix convenience function and fix gpt-oss (#20912)

2026-03-23 22:21:47 -05:00

chat-auto-parser-helpers.h

chat : avoid including json in chat.h (#21306)

2026-04-03 09:07:59 +03:00

chat-auto-parser.h

common : delegate assistant continuation to underlying template handlers (#23089)

2026-05-17 13:36:05 +02:00

chat-diff-analyzer.cpp

common/autoparser: fixes for newline handling / forced tool calls (#22654)

2026-05-04 13:18:11 +02:00

chat-peg-parser.cpp

common : delegate assistant continuation to underlying template handlers (#23089)

2026-05-17 13:36:05 +02:00

chat-peg-parser.h

common : enable streaming JSON argument values (#23173)

2026-05-17 03:44:34 -05:00

chat.cpp

common : delegate assistant continuation to underlying template handlers (#23089)

2026-05-17 13:36:05 +02:00

chat.h

common : delegate assistant continuation to underlying template handlers (#23089)

2026-05-17 13:36:05 +02:00

CMakeLists.txt

fit-params : refactor + add option to output estimated memory per device (#22171)

2026-04-21 09:54:36 +03:00

common.cpp

llama : MTP clean-up (#23269)

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

common.h

llama : MTP clean-up (#23269)

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

console.cpp

cli: fix stripping of \n in multiline input (#21485)

2026-04-06 20:54:06 +02:00

console.h

cli : add command and file auto-completion (#19985)

2026-03-05 10:47:28 +01:00

debug.cpp

common: fix missing exports in llama-common (#22340)

2026-04-27 08:06:39 +03:00

debug.h

common: fix missing exports in llama-common (#22340)

2026-04-27 08:06:39 +03:00

download.cpp

llama + spec: MTP Support (#22673)

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

download.h

llama + spec: MTP Support (#22673)

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

fit.cpp

logs : reduce (#23021)

2026-05-14 13:05:52 +03:00

fit.h

fit-params : refactor + add option to output estimated memory per device (#22171)

2026-04-21 09:54:36 +03:00

hf-cache.cpp

common : remove hf cache migration (#23266)

2026-05-18 17:11:47 +02:00

hf-cache.h

common : remove hf cache migration (#23266)

2026-05-18 17:11:47 +02:00

http.h

server: Parse port numbers from MCP server URLs in CORS proxy (#20208)

2026-03-09 17:47:54 +01:00

json-partial.cpp

common : Generalized XML-style tool-call parsing with streaming support (GLM 4.5/4.6 + MiniMax M2 + SeedOSS + Kimi-K2 + Qwen3-Coder + Apriel-1.5 + Xiaomi-MiMo) (#16932)

2025-11-18 18:54:15 +01:00

json-partial.h

cli : fix reasoning responses in CLI (#18961)

2026-01-20 18:23:25 +01:00

json-schema-to-grammar.cpp

common/json-schema: fix: handle non-capturing groups (?:...) in JSON schema pattern converter (#21124)

2026-03-28 17:55:38 +01:00

json-schema-to-grammar.h

common : add nemotron 3 parsing (#18077)

2025-12-16 04:05:23 -06:00

llguidance.cpp

sampling : add support for backend sampling (#17004)

2026-01-04 22:22:16 +02:00

log.cpp

logs : reduce (#23021)

2026-05-14 13:05:52 +03:00

log.h

logs : reduce (#23021)

2026-05-14 13:05:52 +03:00

ngram-cache.cpp

spec : add self‑speculative decoding (no draft model required) + refactor (#18471)

2026-01-28 19:42:42 +02:00

ngram-cache.h

spec : add self‑speculative decoding (no draft model required) + refactor (#18471)

2026-01-28 19:42:42 +02:00

ngram-map.cpp

llama : MTP clean-up (#23269)

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

ngram-map.h

fix: correct misspellings in code comments (#21217)

2026-03-31 13:50:51 +02:00

ngram-mod.cpp

spec : add ngram-mod (#19164)

2026-01-30 18:21:48 +02:00

ngram-mod.h

ngram-mod : fix build [no ci] (#19216)

2026-01-30 21:27:27 +02:00

peg-parser.cpp

common/gemma4 : handle parsing edge cases (#21760)

2026-04-13 18:18:18 -05:00

peg-parser.h

common/gemma4 : handle parsing edge cases (#21760)

2026-04-13 18:18:18 -05:00

preset.cpp

mtmd, server, common: expose modalities to /v1/models (#22952)

2026-05-12 19:08:07 +02:00

preset.h

mtmd, server, common: expose modalities to /v1/models (#22952)

2026-05-12 19:08:07 +02:00

reasoning-budget.cpp

reasoning-budget: clone should do a deep-copy (#23095)

2026-05-15 11:59:07 +02:00

reasoning-budget.h

common : do not pass prompt tokens to reasoning budget sampler (#22488)

2026-04-29 14:10:58 -05:00

regex-partial.cpp

common : fix iterator::end() dereference (#20445)

2026-03-16 08:50:38 +02:00

regex-partial.h

common: add partial regex support (#12808)

2025-05-14 19:50:57 +01:00

sampling.cpp

backend sampling: support returning post-sampling probs (#22622)

2026-05-10 19:12:02 +02:00

sampling.h

common : do not pass prompt tokens to reasoning budget sampler (#22488)

2026-04-29 14:10:58 -05:00

speculative.cpp

llama : MTP clean-up (#23269)

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

speculative.h

llama: avoid copying logits during prompt decode in MTP (#23198)

2026-05-17 23:30:25 +08:00

unicode.cpp

common/parser: handle reasoning budget (#20297)

2026-03-11 10:26:12 +01:00

unicode.h

common/parser: handle reasoning budget (#20297)

2026-03-11 10:26:12 +01:00