Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

35ec7f0
Fix incremental build file deps (#7361)
Daniel Hiltgen committed 2 years ago
5231ae5
Improve dependency gathering logic (#7345)
Daniel Hiltgen committed 2 years ago
3085c47
fix #7247 - invalid image input (#7249)
Bill Wang committed 2 years ago
0ccc732
integration: harden embedding test (#7306)
Daniel Hiltgen committed 2 years ago
dc6fe82
d78fb62
5c44461
03e40ef
server: allow vscode-webview origin (#7273)
Jeffrey Morgan committed 2 years ago
48708ca
image processing for llama3.2 (#6963)
Patrick Devine committed 2 years ago
c7cb0f0
llama: Decouple patching script from submodule (#7139)
Daniel Hiltgen committed 2 years ago
bf4018b
llama: add compiler tags for cpu features (#7137)
Daniel Hiltgen committed 2 years ago
f86d00c
IBM granite/granitemoe architecture support (#6760)
Gabe Goodhart committed 2 years ago
f2890a4
Rename gpu package discover (#7143)
Daniel Hiltgen committed 2 years ago
05cd82e
Move macos v11 support flags to build script (#7203)
Daniel Hiltgen committed 2 years ago
7d6eb0d
24636df
1d7fa3a
Add missing BF16 tensor type. (#7193)
frob committed 2 years ago
09035b7
Track GPU discovery failure information (#5820)
Daniel Hiltgen committed 2 years ago
f3c8b89
Fix regression on older macos versions (#7192)
Daniel Hiltgen committed 2 years ago
5dd0477
llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174)
Daniel Hiltgen committed 2 years ago
c3d321d
cli: Send all images in conversation history
Jesse Gross committed 2 years ago
7fe3902
0077e22
server: Don't clear cmd when closing a server
Jesse Gross committed 2 years ago
03408f3
fix vendoring attribute for metal (#7156)
Daniel Hiltgen committed 2 years ago
cd7e01e
fix vendoring attribute (#7155)
Daniel Hiltgen committed 2 years ago
7a962bd
Fix build leakages (#7141)
Daniel Hiltgen committed 2 years ago
f9584de
Re-introduce the `llama` package (#5034)
Jeffrey Morgan committed 2 years ago
96efd90
de98261