Skip to content

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

Commits on main

add registries for parsers/renderers
Devon Rifkin committed 1 year ago
ddaca64
05982a9
runner: fix shifting on llama runner (#12604)
Jeffrey Morgan committed 1 year ago
e638f2a
Revert "use llama runner for qwen3 (#12556)"
Michael Yang committed 1 year ago
18087f2
fix(qwen3): deepseek distill
Michael Yang committed 1 year ago
6c833d5
Reapply "add truncate and shift parameters" (#12582)
Jeffrey Morgan committed 1 year ago
6544e14
routes: fix built-in renderers for `api/generate`
Devon Rifkin committed 1 year ago
6db8da9
discover: fix typo (#12565)
frob committed 1 year ago
0c68ec8
doc: remove AMD EOL GPUs (#12567)
Daniel Hiltgen committed 1 year ago
70d9e36
ollamarunner: fix deadlock
Michael Yang committed 1 year ago
1a2feb2
implement nvml for linux (#12517)
Daniel Hiltgen committed 1 year ago
aab2190
comment split
Michael Yang committed 1 year ago
629db9d
fix test
Michael Yang committed 1 year ago
e0cd511
fix lint
Michael Yang committed 1 year ago
2073320
convert: slice gate_up weight
Michael Yang committed 1 year ago
9308512
convert: split gate_up bias
Michael Yang committed 1 year ago
c00fa9c
refactor: using testing.B.Loop
yajianggroup committed 1 year ago
df411c4
use llama runner for qwen3 (#12556)
Jeffrey Morgan committed 1 year ago
3d32249
refactor: use builtin max and min
shengxinjing committed 1 year ago
47298fc
refactor: use builtin max and min
shengxinjing committed 1 year ago
4a48937
ollamarunner: measure only active time
Michael Yang committed 1 year ago
967a82f
llamarunner: update metrics
Michael Yang committed 1 year ago
bbbc73d
routes: structured outputs for gpt-oss (#12460)
Parth Sareen committed 1 year ago
77060d4
1b91d4d
7d96525
add truncate and shift parameters (#12519)
Jeffrey Morgan committed 1 year ago
6a62b89