Skip to content

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

Commits on main

ggml: Temporarily disable reporting UUIDs
Jesse Gross committed 1 year ago
45f216a
skip quantizing per_layer_token_embd (#11207)
Michael Yang committed 1 year ago
d0b32de
ci: multi-stage release process (#11001)
Daniel Hiltgen committed 1 year ago
11ffc36
fs/ggml: add multiplier in graph estimates (#11208)
Jeffrey Morgan committed 1 year ago
ba04902
add new gemma model (#11204)
Michael Yang committed 1 year ago
73b642e
ci: arm sbsa fixes (#11194)
Daniel Hiltgen committed 1 year ago
ad118d8
ci: include dependencies
Daniel Hiltgen committed 1 year ago
f085341
ci: pick up arm sbsa cuda libs (#11192)
Daniel Hiltgen committed 1 year ago
4b4a90f
ci: recombine linux amd64 binaries (#11188)
Daniel Hiltgen committed 1 year ago
03274a6
ci: rocm parallel builds on windows (#11187)
Daniel Hiltgen committed 1 year ago
405d2f6
a3f7dd3
CI: switch windows to vs 2022 (#11184)
Daniel Hiltgen committed 1 year ago
c85c0eb
avoid context overflow (#11175)
Daniel Hiltgen committed 1 year ago
10a8e04
Re-remove cuda v11 (#10694)
Daniel Hiltgen committed 1 year ago
1c6669e
b2b270a
build speedups (#11142)
Daniel Hiltgen committed 1 year ago
65bff66
convert: utility for merging tensors (#11069)
Michael Yang committed 1 year ago
c088ac0
ggml: Check return status for computation.
Jesse Gross committed 1 year ago
87b7af6
int: add coverage for older models (#11137)
Daniel Hiltgen committed 1 year ago
f2527b0
benchmark: remove unused benchmark test (#11120)
Jeffrey Morgan committed 1 year ago
8bcb312
6baf1e3
Revert "ggml: Export GPU UUIDs" (#11115)
Jeffrey Morgan committed 1 year ago
ed567ef
a6e64fb
60cfa2a
55bbf3b
6bda1d2