Jeff Bolz
|
303f8615e9
vulkan: Multi-pass softmax for large number of cols (#17892)
|
1 maand geleden |
Georgi Gerganov
|
3c6391e748
speculative-simple : free batch on exit (#17985)
|
1 maand geleden |
Sigbjørn Skjæret
|
8e4d678528
common : skip model validation when --completion-bash is requested (#17975)
|
1 maand geleden |
Jeff Bolz
|
07a10c1090
vulkan: Allow non-pow2 n_experts in topk_moe (#17872)
|
1 maand geleden |
Sigbjørn Skjæret
|
2bc94e7928
add llama-completion to completion-bash executables (#17976)
|
1 maand geleden |
Daniel Bevenius
|
fd1085ffb7
model-conversion : use CONVERTED_MODEL value for converted model [no ci] (#17984)
|
1 maand geleden |
Xuan-Son Nguyen
|
380b4c984e
common: support negated args (#17919)
|
1 maand geleden |
Xuan-Son Nguyen
|
e39a2ce66d
clip: move model cgraphs into their own files (#17965)
|
1 maand geleden |
jiahao su
|
a8c7f33d79
ci : change the cann version and the container pull method (#17953)
|
1 maand geleden |
Sigbjørn Skjæret
|
b7f5f46e03
docker : include legacy llama-completion binary (#17964)
|
1 maand geleden |
Johannes Gäßler
|
482211438d
CUDA: fix overflow in MMA kernel without stream-k (#17939)
|
1 maand geleden |
Georgi Gerganov
|
7bed317f53
models : fix the attn_factor for mistral3 graphs + improve consistency (#17945)
|
1 maand geleden |
Sigbjørn Skjæret
|
dcb7d17758
cann : fix ops broken by circular padding guard (#17825)
|
1 maand geleden |
ixgbe
|
51604435e8
ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951)
|
1 maand geleden |
Xuan-Son Nguyen
|
17158965ac
mtmd: explicitly forbidden inclusion of private header and libcommon (#17946)
|
1 maand geleden |
Aleksander Grygier
|
12280ae905
webui: Fix parsing non-LaTeX occurrencies of `\(` or `\)` (#17810)
|
1 maand geleden |
Xuan-Son Nguyen
|
54a0fee4b7
arg: add -mm and -mmu as short form of --mmproj and --mmproj-url (#17958)
|
1 maand geleden |
Daniel Bevenius
|
dada4c846d
model-conversion : remove max diff check in compare-logits [no ci] (#17954)
|
1 maand geleden |
Adrien Gallouët
|
b8ee22cfde
common : add minimalist multi-thread progress bar (#17602)
|
1 maand geleden |
Gustavo Rocha Dias
|
2eaa2c65cb
cmake: link ws2_32 for MinGW/w64devkit builds in cpp-httplib (#17949)
|
1 maand geleden |
yulo
|
c33a58bced
HIP: enable mmf for RDNA3 (#17879)
|
1 maand geleden |
Pascal
|
a81a569577
Add a search field on model selector / improve mobile display (#17765)
|
1 maand geleden |
Piotr Wilkin (ilintar)
|
53ecd4fdb9
SOLVE_TRI extension to more dimensions (#17793)
|
1 maand geleden |
Georgi Gerganov
|
c6f6e4f96a
ggml-alloc : fix reuse-parent logic for misaligned sizes (#17884)
|
1 maand geleden |
Georgi Gerganov
|
d9f8f60618
batch : fix sequence id ownership (#17915)
|
1 maand geleden |
Yuichiro Utsumi
|
e4ae383317
docs: use port 8080 in Docker examples (#17903)
|
1 maand geleden |
nullname
|
34ce48d97a
ggml-hexagon: fix `rope` failure at `test-backend-ops` (#17565)
|
1 maand geleden |
Sigbjørn Skjæret
|
45e350e3d3
ci: fix riscv64-native build (#17916)
|
1 maand geleden |
Xuan-Son Nguyen
|
c6b2c9310c
mtmd: some small clean up (#17909)
|
1 maand geleden |
Xuan-Son Nguyen
|
34a6d86982
cli: enable jinja by default (#17911)
|
1 maand geleden |