Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
x/create: quantize a draft model's output head at the requested type
132e0ca Jesse Gross committed 3 months ago
qwen3_5: decode each expert tensor with its own quantization format
d6f69da Jesse Gross committed 4 months ago
server: fix ps data race on scheduler loaded map (#17376)
6cd4000 Daniel Hiltgen committed 3 months ago
test: harden flaky updater and transfer unit tests (#17378)
a84b315 Daniel Hiltgen committed 3 months ago
x/create: quantize lm_head at 8-bit in the requested family
83d4311 Jesse Gross committed 4 months ago
model/parsers: finalize incomplete GLM tool calls (#17250)
b517b9b Daniel Hiltgen committed 4 months ago
model: add Laguna v8 chat support and fix Metal inference (#17291)
a18c230 Daniel Hiltgen committed 4 months ago
docs: add renderer/parser fields to the API docs (#17275)
e2c2edc Patrick Devine committed 4 months ago
cmd/tui/chat: render bold emphasis consistently across markdown (#17224)
0de3819 Parth Sareen committed 4 months ago