Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
llm: attempt to evaluate symlinks, but do not fail (#9089)
5296f48 Jeffrey Morgan committed 1 year ago
llm: do not evaluate symlink for exe path lookup (#9088)
f05774b Jeffrey Morgan committed 1 year ago
ggml-backend: Ensure data is available after async computation
6083069 Jesse Gross committed 1 year ago
backend: Support graph computation that does not return an output
4d4463b Jesse Gross committed 1 year ago
backend: Consistently use int (vs. int64) for tensor shapes
0e38297 Jesse Gross committed 1 year ago
openai: finish_reason as tool_calls for streaming with tools (#7963)
10d59d5 Anuraag (Rag) Agrawal committed 1 year ago
build: add -DGGML_CUDA_NO_PEER_COPY=ON for rocm builds on windows (#9060)
a4f69a0 Jeffrey Morgan committed 1 year ago
ml/backend/ggml: fix crash on dlopen for non-AVX systems (#8976)
f4711da Jeffrey Morgan committed 1 year ago
readme: add Lunary to observability community integrations (#8975)
38117fb Hugues Chocart committed 1 year ago
docs: link directly to latest release page for tdm-gcc (#8939)
b86c0a1 Jeffrey Morgan committed 1 year ago