Samuel Oliveira Alves 0a415bde4a Feat: Llama-cli Spec (#2081) ...

* feat: implement speculative decoding support in llama-cli

* fix spec mismatchs and metrics

2026-07-06 09:46:18 +02:00

..

baby-llama

…

batched

…

batched-bench

…

batched.swift

…

benchmark

…

convert-llama2c-to-ggml

…

cvector-generator

Split mode graph for dense Gemma4 assistant (#2022)

2026-06-24 18:29:32 +02:00

deprecation-warning

…

embedding

…

eval-callback

…

export-lora

…

gbnf-validator

…

gguf

…

gguf-hash

…

gguf-split

…

gritlm

…

imatrix

…

infill

…

jeopardy

…

llama-bench

…

llama.android

…

llama.swiftui

…

lookahead

…

lookup

…

main

Feat: Llama-cli Spec (#2081)

2026-07-06 09:46:18 +02:00

main-cmake-pkg

…

mtmd

Free raw multimedia data from server_tokens after encoding, as it will never be read again (#2029)

2026-06-25 10:18:32 +02:00

parallel

…

parser

…

passkey

…

perplexity

…

quantize

…

quantize-stats

…

retrieval

…

rpc

fix(rpc): update ggml_backend_cuda_init to 3-arg signature (#2084)

2026-07-06 09:26:45 +02:00

save-load-state

…

server

Normalize disabled context-shift overflow error (#2051)

2026-06-29 08:30:05 +02:00

simple

…

speculative

…

sweep-bench

…

sycl

…

tokenize

…

base-translate.sh

…

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

…

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

…

convert_legacy_llama.py

…

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

…

llama.vim

…

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar_examples.py

…

pydantic_models_to_grammar.py

…

reason-act.sh

…

regex_to_grammar.py

…

server_embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…