Releases: phymbert/llama.cpp
Releases · phymbert/llama.cpp
b2447
ggml : add AVX512F SIMD (#6088)
b2381
server : print chat template info
b2370
server : simplify logic for empty prompts (#5953)
b2346
server: tests: schedule slow dispatch
b2230
examples : do not assume BOS when shifting context (#5622)
b2203
examples : support minItems/maxItems in JSON grammar converter (#5039) * support minLength and maxLength in JSON schema grammar converter * Update examples/json-schema-to-grammar.py --------- Co-authored-by: Georgi Gerganov <[email protected]>