 Sigbjørn Skjæret
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 months ago |
 Georgi Gerganov
|
432cf4304c
codeowners : update + cleanup (#16174)
|
4 months ago |
 Adrien Gallouët
|
37a23c17bd
common : enable `--offline` mode without curl support (#16137)
|
4 months ago |
 Quentin Bramas
|
138c87ce8b
webui : fix handling incomplete chunks (#16107)
|
4 months ago |
 GideonSerf
|
c6db9a1027
embedding : fix typos in README (#16171)
|
4 months ago |
 Haiyue Wang
|
d05affbab7
common : remove unused local variables (#16140)
|
4 months ago |
|
Georgi Gerganov
|
4f324a556c
ggml : extend ggml_can_fuse to work with non-sequential nodes (#16123)
|
4 months ago |
|
Georgi Gerganov
|
a71ae3ba7a
ggml : add ggml_op_is_empty (#16122)
|
4 months ago |
 Xuan-Son Nguyen
|
05a2458121
codeowners : update ownership for @ngxson and @allozuar (#16128)
|
4 months ago |
 Shin-myoung-serp
|
96fdca043b
Vulkan: add conv_transpose_2d operation (#16022)
|
4 months ago |
|
Sigbjørn Skjæret
|
b2d980fce0
codeowners : claim responsibility for ci, models, gguf-py and convert (#16124)
|
4 months ago |
|
Georgi Gerganov
|
5c6106a696
contrib : update roles (#16113)
|
4 months ago |
|
Georgi Gerganov
|
ec65fb52f0
ci : remove vulkaninfo calls (#16169)
|
4 months ago |
|
Georgi Gerganov
|
1d660d2fae
ci : use smaller model (#16168)
|
4 months ago |
 Jeff Bolz
|
a20d810d79
vulkan: add RTE variants of exp shader (#16165)
|
4 months ago |
|
Georgi Gerganov
|
4d0a7cbc61
ci : adjust params for less runtime (#16167)
|
4 months ago |
 Ruben Ortlam
|
9073a73d82
vulkan: vec dot matrix multiplication fix (#16151)
|
4 months ago |
 lhez
|
51f5a45fbe
opencl: fix concat crash on win arm64 with Adreno (#15944)
|
4 months ago |
|
lhez
|
c4510dc937
opencl: initial `q8_0` mv support (#15732)
|
4 months ago |
|
Georgi Gerganov
|
da30ab5f86
ci : add label for the RISC-V runner (#16150)
|
4 months ago |
|
Georgi Gerganov
|
28baac9c9f
ci : migrate ggml ci to self-hosted runners (#16116)
|
4 months ago |
 Giuseppe Scrivano
|
1eeb523c3e
vulkan: optimize UMA buffer operations and fix driver hangs (#16059)
|
4 months ago |
|
Jeff Bolz
|
5bb4a3edec
vulkan: fix validation error about VK_PIPELINE_CREATE_CAPTURE_STATISTICS_BIT_KHR (#16086)
|
4 months ago |
|
Georgi Gerganov
|
7f766929ca
sync : ggml
|
4 months ago |
 Daniel Bevenius
|
405921dcef
ggml : introduce semantic versioning (ggml/1336)
|
4 months ago |
 Gregor Jasny
|
fa6383ca7e
CUDA : conditionally add cuda architectures (ggml/1341)
|
4 months ago |
|
Ruben Ortlam
|
803dac2e48
vulkan: use vec dot for matrix matrix multiplications (#16056)
|
4 months ago |
 Benni
|
459c0c2c1a
server: fix SSE and OpenAI compatibility for error messages when streaming (#16109)
|
4 months ago |
 ssweens
|
be79d9fdd9
llama-bench: add --devices and --list-devices support (#16039)
|
4 months ago |
 shun095
|
f432d8d83e
chat: Fix streaming parser for granite models (#15682)
|
4 months ago |
