Tags
Tags give the ability to mark specific points in history as being important
master-416-614f873
614f8736
·
sync: update ggml (#1082)
·
Dec 14, 2025
master-415-d96b415
d96b4152
·
perf: optimize ggml_ext_chunk (#1084)
·
Dec 14, 2025
master-414-8f05f5b
8f05f5bc
·
feat: add support for custom scheduler (#694)
·
Dec 13, 2025
master-413-15d0f82
15d0f827
·
feat(server): do not parse lora fromt client-side prompts (#1083)
·
Dec 13, 2025
master-412-6888fcb
6888fcb5
·
feat: server add default_gen_params to override default args (#1050)
·
Dec 13, 2025
master-411-2aecdd5
2aecdd57
·
feat: simple openai image generation api compatiple server (#1037)
·
Dec 13, 2025
master-410-11ab095
11ab0952
·
fix: resolve embedding loading issue when calling generate_image multiple times (#1078)
·
Dec 12, 2025
master-409-a3a88fc
a3a88fc9
·
fix: avoid crash loading LoRAs with bf16 weights (#1077)
·
Dec 12, 2025
master-408-8823dc4
8823dc48
·
feat: align the spatial size to the corresponding multiple (#1073)
·
Dec 10, 2025
master-407-1ac5a61
1ac5a616
·
feat: support custom upscale tile size (#896)
·
Dec 10, 2025
master-406-d939f6e
d939f6e8
·
refactor: optimize the handling of LoRA models (#1070)
·
Dec 10, 2025
master-405-e72aea7
e72aea79
·
feat: embed version string and git commit hash (#1008)
·
Dec 09, 2025
master-403-583a02e
583a02e2
·
feat: add Flux.2 VAE proj matrix for previews (#1017)
·
Dec 09, 2025
master-402-96c3e64
96c3e640
·
refactor: optimize the handling of embedding (#1068)
·
Dec 08, 2025
master-401-0392273
0392273e
·
chore: add compute kernels to Windows CUDA build (#1062)
·
Dec 07, 2025
master-398-2f0bd31
2f0bd31a
·
feat: add ovis image support (#1057)
·
Dec 07, 2025
master-397-bfbb929
bfbb9297
·
feat: do not convert bf16 to f32 (#1055)
·
Dec 06, 2025
master-396-689e44c
689e44c9
·
fix: correct ggml_ext_silu_act (#1056)
·
Dec 06, 2025
master-395-985aedd
985aedda
·
refactor: optimize the handling of pred type (#1048)
·
Dec 04, 2025
master-394-3f3610b
3f3610b5
·
chore: optimize lora log (#1047)
·
Dec 04, 2025
1
2
3
4
5
6
7
8
…
19