Releases: ggerganov/llama.cpp
Releases · ggerganov/llama.cpp
b3039
metal : add missing asserts (#7617)
b3038
ggml : fix YARN + add tests + add asserts (#7617) * tests : add rope tests ggml-ci * ggml : fixes (hopefully) ggml-ci * tests : add non-cont tests ggml-ci * cuda : add asserts for rope/norm + fix DS2 ggml-ci * ggml : assert contiguousness * tests : reduce RoPE tests ggml-ci
b3037
cuda : non-cont concat support (#7610) * tests : add non-cont concat tests * cuda : non-cont concat support ggml-ci
b3036
llama-bench : add support for the RPC backend (#7435)
b3035
ggml : use atomic_flag for critical section (#7598) * ggml : use atomic_flag for critical section * add windows shims
b3033
sync : ggml
b3030
ggml : fix typo in ggml.c (#7603)
b3029
[SYCL] Align GEMM dispatch (#7566) * align GEMM dispatch
b3028
Tokenizer WPM fixes (#7500) * Update random test: add_bos_token. * Update random test: add WPM models for testing. * Build vocab.special_tokens_cache using vocab token types. * Fix and improve WPM preprocessing. - Fix unicode edge case combinations. - Split by whitspace in the same pass. * Discard all tokens when no matching found.
b3027
sycl : fix assert (#7563)