Skip to content

Releases: phymbert/llama.cpp

b2447

16 Mar 19:30
c47cf41
Compare
Choose a tag to compare
ggml : add AVX512F SIMD (#6088)

b2381

09 Mar 21:37
77d1ac7
Compare
Choose a tag to compare
server : print chat template info

b2370

09 Mar 11:15
9674aaf
Compare
Choose a tag to compare
server : simplify logic for empty prompts (#5953)

b2346

02 Mar 21:59
Compare
Choose a tag to compare
server: tests: schedule slow dispatch

b2230

21 Feb 18:02
89febfe
Compare
Choose a tag to compare
examples : do not assume BOS when shifting context (#5622)

b2203

19 Feb 19:10
9d679f0
Compare
Choose a tag to compare
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]>