Skip to content

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

Commits on main

sched: logging improvements (#10550)
Daniel Hiltgen committed 1 year ago
76ea735
readme: add llama 4 models (#10530)
aritra saha committed 1 year ago
dd1d4e9
c2f5d66
llama: update to commit e1e8e099 (#10513)
Jeffrey Morgan committed 1 year ago
8dd12c8
kvcache: Log batch size if we can't find a slot
Jesse Gross committed 1 year ago
074bac8
8e8f2c6
readme: change granite3.2 to granite3.3 (#10525)
aritra saha committed 1 year ago
d5d5f0c
fix: write gguf padding (#10510)
Michael Yang committed 1 year ago
a7835c6
Fix "Stopping..." scheduler hang (#10487)
Daniel Hiltgen committed 1 year ago
415c8fc
Narrow set of paths we load GGML from (#10485)
Daniel Hiltgen committed 1 year ago
718eda1
all: update several golang.org/x packages (#10436)
batuhankadioglu committed 1 year ago
7b68e25
7bec272
readme: fix typos (#10399)
crStiv committed 1 year ago
6bf0b81
db428ad
lower default num parallel to 2
Devon Rifkin committed 1 year ago
fe5b9bb
config: update default context length to 4096
Devon Rifkin committed 1 year ago
44b466e
dd93e1a
d2ee599
ggml: fix crash for array head counts
Devon Rifkin committed 1 year ago
6ed8898
model: fix build (#10416)
Michael Yang committed 1 year ago
5cfc1c3
memory
Michael Yang committed 1 year ago
f0ad49e