mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 11:24:35 +00:00
Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template types (#10572)
docker.yml #1333:Scheduled
Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` chat template types (#10572)
close-issue.yml #1332:Scheduled
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (#10567)
docker.yml #1331:Scheduled
ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_q4_0_4x4_q8_0() (#10567)
close-issue.yml #1330:Scheduled