Diego Devesa
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
1 éve |
Xuan Son Nguyen
|
b782e5c7d4
server : add more test cases (#10569)
|
1 éve |
Robert Collins
|
3a8e9af402
imatrix : support combine-only (#10492)
|
1 éve |
Diego Devesa
|
a3a3048e7a
cleanup UI link list (#10577)
|
1 éve |
Georgi Gerganov
|
f0678c5ff4
ggml : fix I8MM Q4_1 scaling factor conversion (#10562)
|
1 éve |
Shupei Fan
|
4b3242bbea
ggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (#10580)
|
1 éve |
Alberto Cabrera Pérez
|
0f77aae560
sycl : offload of get_rows set to 0 (#10432)
|
1 éve |
Alberto Cabrera Pérez
|
266b8519ee
sycl : Reroute permuted mul_mats through oneMKL (#10408)
|
1 éve |
Chenguang Li
|
938f608742
CANN: RoPE operator optimization (#10563)
|
1 éve |
Jeff Bolz
|
f095a649ec
vulkan: get the first command buffer submitted sooner (#10499)
|
1 éve |
Ting Lou
|
678d7994f4
llava: return false instead of exit (#10546)
|
1 éve |
Georgi Gerganov
|
dc22344088
ggml : remove redundant copyright notice + update authors
|
1 éve |
Georgi Gerganov
|
4c0a95b107
llama : add missing model types
|
1 éve |
Xuan Son Nguyen
|
6c59567689
server : (tests) don't use thread for capturing stdout/stderr, bump openai client library (#10568)
|
1 éve |
Johannes Gäßler
|
890719311b
common: fix warning message when no GPU found (#10564)
|
1 éve |
Random Fly
|
7281cf13ad
docs: fix outdated usage of llama-simple (#10565)
|
1 éve |
Diego Devesa
|
e90688edd0
ci : fix tag name in cuda and hip releases (#10566)
|
1 éve |
Georgi Gerganov
|
76b27d29c2
ggml : fix row condition for i8mm kernels (#10561)
|
1 éve |
Georgi Gerganov
|
eea986f215
cmake : fix ARM feature detection (#10543)
|
1 éve |
Shupei Fan
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 éve |
Sergio López
|
2025fa67e9
kompute : improve backend to pass test_backend_ops (#10542)
|
1 éve |
Ruixin Huang
|
c6bc73951e
CANN: Update cann.md to display correctly in CLion (#10538)
|
1 éve |
leo-pony
|
605fa66c50
CANN: Fix SOC_TYPE compile bug (#10519)
|
1 éve |
Chenguang Li
|
b7420131bf
CANN: ROPE operator optimization (#10540)
|
1 éve |
Xuan Son Nguyen
|
9f912511bc
common : fix duplicated file name with hf_repo and hf_file (#10550)
|
1 éve |
uvos
|
3ad5451f3b
Add some minimal optimizations for CDNA (#10498)
|
1 éve |
Diego Devesa
|
46c69e0e75
ci : faster CUDA toolkit installation method and use ccache (#10537)
|
1 éve |
Georgi Gerganov
|
9e2301f4a4
metal : fix group_norm support condition (#0)
|
1 éve |
Georgi Gerganov
|
fee824a1a1
sync : ggml
|
1 éve |
Frankie Robertson
|
9150f8fef9
Do not include arm_neon.h when compiling CUDA code (ggml/1028)
|
1 éve |