Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
server: verify digest is not empty on create (#14555)
23d4cad Bruce MacDonald committed 8 months ago
runner: add token history sampling parameters to ollama runner (#14537)
86513cb Jeffrey Morgan committed 8 months ago
model/qwen3next: avoid crash in in DeltaNet when offloading (#14541)
3490e95 Jeffrey Morgan committed 8 months ago
qwen3next: add compatibility with imported GGUF models (#14517)
8da09b1 Jeffrey Morgan committed 8 months ago
mlxrunner: Propagate pipeline errors to client via api.StatusError
18ab09b Jesse Gross committed 8 months ago
model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)
cc90a03 Parth Sareen committed 8 months ago
fix: window app crash on startup when update is pending (#14451)
d69ddc1 Eva H committed 8 months ago
mlxrunner: Cancel in-flight requests when the client disconnects
0f23b7b Jesse Gross committed 8 months ago
mlx: don't default to affine quantization for unquantized models
f20dc6b Jesse Gross committed 9 months ago
mlxrunner: Fix duplicate log prefixes and reduce log noise
8daf47f Jesse Gross committed 9 months ago
mlxrunner: Simplify KV cache to single-entry prefix matching
5c73c4e Jesse Gross committed 9 months ago
mlxrunner: Fix memory leaks with pin/sweep lifecycle management
5daf59c Jesse Gross committed 9 months ago
cmd/config: install web search plugin to user-level extensions dir (#14362)
06edabd Parth Sareen committed 9 months ago
mlx: remove noisy error output from dynamic library loading (#14346)
8b4e5a8 Jeffrey Morgan committed 9 months ago