 Shupei Fan
|
c202cef168
ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)
|
1 anno fa |
 Sergio López
|
2025fa67e9
kompute : improve backend to pass test_backend_ops (#10542)
|
1 anno fa |
 Ruixin Huang
|
c6bc73951e
CANN: Update cann.md to display correctly in CLion (#10538)
|
1 anno fa |
 leo-pony
|
605fa66c50
CANN: Fix SOC_TYPE compile bug (#10519)
|
1 anno fa |
 Chenguang Li
|
b7420131bf
CANN: ROPE operator optimization (#10540)
|
1 anno fa |
 Xuan Son Nguyen
|
9f912511bc
common : fix duplicated file name with hf_repo and hf_file (#10550)
|
1 anno fa |
 uvos
|
3ad5451f3b
Add some minimal optimizations for CDNA (#10498)
|
1 anno fa |
 Diego Devesa
|
46c69e0e75
ci : faster CUDA toolkit installation method and use ccache (#10537)
|
1 anno fa |
 Georgi Gerganov
|
9e2301f4a4
metal : fix group_norm support condition (#0)
|
1 anno fa |
|
Georgi Gerganov
|
fee824a1a1
sync : ggml
|
1 anno fa |
 Frankie Robertson
|
9150f8fef9
Do not include arm_neon.h when compiling CUDA code (ggml/1028)
|
1 anno fa |
 Jeff Bolz
|
c31ed2abfc
vulkan: define all quant data structures in types.comp (#10440)
|
1 anno fa |
|
Jeff Bolz
|
5b3466bedf
vulkan: Handle GPUs with less shared memory (#10468)
|
1 anno fa |
|
Jeff Bolz
|
249a7902ec
vulkan: further optimize q5_k mul_mat_vec (#10479)
|
1 anno fa |
|
Jeff Bolz
|
71a64989a5
vulkan: skip integer div/mod in get_offsets for batch_idx==0 (#10506)
|
1 anno fa |
|
Jeff Bolz
|
4a57d362e1
vulkan: optimize Q2_K and Q3_K mul_mat_vec (#10459)
|
1 anno fa |
|
Diego Devesa
|
c9b00a70b0
ci : fix cuda releases (#10532)
|
1 anno fa |
 Shane A
|
de5097351c
Add OLMo 2 model in docs (#10530)
|
1 anno fa |
|
Diego Devesa
|
5a349f2809
ci : remove nix workflows (#10526)
|
1 anno fa |
|
Diego Devesa
|
30ec398321
llama : disable warnings for 3rd party sha1 dependency (#10527)
|
1 anno fa |
 Tristan Druyen
|
be0e350c8b
Fix HIP flag inconsistency & build docs (#10524)
|
1 anno fa |
 R0CKSTAR
|
249cd93da3
mtgpu: Add MUSA_DOCKER_ARCH in Dockerfiles && update cmake and make (#10516)
|
1 anno fa |
|
Jeff Bolz
|
904109ed0d
vulkan: fix group_norm (#10496)
|
1 anno fa |
|
Xuan Son Nguyen
|
45abe0f74e
server : replace behave with pytest (#10416)
|
1 anno fa |
 Neo Zhang Jianyu
|
0bbd2262a3
restore the condistion to build & update pacakge when merge (#10507)
|
1 anno fa |
|
Georgi Gerganov
|
ab96610b1e
cmake : enable warnings in llama (#10474)
|
1 anno fa |
|
Diego Devesa
|
7db3846a94
ci : publish the docker images created during scheduled runs (#10515)
|
1 anno fa |
|
Diego Devesa
|
c6807b3f28
ci : add ubuntu cuda build, build with one arch on windows (#10456)
|
1 anno fa |
 Charles Xu
|
25669aa92c
ggml-cpu: cmake add arm64 cpu feature check for macos (#10487)
|
1 anno fa |
|
Georgi Gerganov
|
84e1c33cde
server : fix parallel speculative decoding (#10513)
|
1 anno fa |
