 Georgi Gerganov
|
a4a0aa5ea2
ggml : fix dependencies for ggml_set_rows (#16318)
|
3 months ago |
 Jeff Bolz
|
92cd103f62
vulkan: Fix validation failure in quantized flash attention (#16292)
|
3 months ago |
 Sigbjørn Skjæret
|
b887d2f341
ggml : fix GGML_F32_VEC_FMA argument order in ggml_vec_mad1_f32 (#16307)
|
3 months ago |
 crat0z
|
bd0af02fc9
common : fix reasoning before forced tool call via tool_choice = required (#16264)
|
3 months ago |
 R0CKSTAR
|
d9e0e7c819
ci : fix musa docker build (#16306)
|
3 months ago |
 Aaron Teo
|
0124ac989f
devops: switch to using ubuntu-22.04-s390x image (#16302)
|
3 months ago |
 Imad Saddik
|
2811c65286
Fixed a few typos in the README of the LLaMA.cpp HTTP Server [no ci] (#16297)
|
3 months ago |
|
Jeff Bolz
|
d8359f5fde
vulkan: 64-bit im2col (#16135)
|
3 months ago |
|
Georgi Gerganov
|
6a2c6145a0
metal : extend mat-mat multiplication support (#16225)
|
3 months ago |
|
Georgi Gerganov
|
3b53634fe3
metal : fuse non-sequential nodes (#16102)
|
3 months ago |
|
Jeff Bolz
|
1384abf8b8
vulkan: handle mat_mul with A matrix > 4GB (#16176)
|
3 months ago |
|
Jeff Bolz
|
e6d65fb02d
vulkan: support arbitrary KV dimension in flash attention (#16160)
|
3 months ago |
 Acly
|
8656f5de68
vulkan : make the vulkan.hpp dynamic dispatcher instance private (#16224)
|
3 months ago |
 Aleksander Grygier
|
4807e8f96a
Show message actions by default (#16289)
|
3 months ago |
 Aman Gupta
|
c0bfc57af4
CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32 (#16277)
|
3 months ago |
 Johannes Gäßler
|
75a3a6c2cd
CUDA: refactor and deduplicate vector FA kernels (#16208)
|
3 months ago |
 Dmytro Minochkin
|
0499b29c6f
vulkan: throw system error instead of SIGABRT during init on older devices (#16156)
|
3 months ago |
 Adrien Gallouët
|
234e2ff8ed
server : remove old LLAMA_SERVER_SSL (#16290)
|
3 months ago |
|
Jeff Bolz
|
3f81b4e91c
vulkan: support GET_ROWS for k-quants (#16235)
|
3 months ago |
|
Adrien Gallouët
|
ace6a54565
build : add LLAMA_OPENSSL option (#16287)
|
3 months ago |
 Vinkal
|
72b24d96c6
model : make minicpm embedding_scale, residual_scale and logit_scale optional with legacy defaults (#16273)
|
3 months ago |
|
Aaron Teo
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
3 months ago |
|
Aleksander Grygier
|
807e8c6d31
Enhance text file detection logic for file attachments (#16199)
|
3 months ago |
|
Aleksander Grygier
|
1a18927894
Allow viewing conversations even when llama server is down (#16255)
|
3 months ago |
 Isaac McFadyen
|
e0539eb6ae
webui: switch to hash-based routing (alternative of #16079) (#16157)
|
3 months ago |
|
Aleksander Grygier
|
5d0a40f390
Always show message actions for mobile UI + improvements for user message sizing (#16076)
|
3 months ago |
 Radoslav Gerganov
|
d12a983659
codeowners : add rgerganov as owner of RPC [no ci] (#16279)
|
3 months ago |
 Aleksei Nikiforov
|
cc1cfa277b
mtmd : fix uninitialized variable in bicubic_resize (#16275)
|
3 months ago |
|
Georgi Gerganov
|
54dbc37053
metal : report OOM errors (#16274)
|
3 months ago |
|
Adrien Gallouët
|
b995a10760
common : use cpp-httplib as a cURL alternative for downloads (#16185)
|
3 months ago |
