 xctan
|
7f09a680af
ggml-cpu : optimize RVV q2_k and q3_k kernels (#16887)
|
2 ay önce |
 Johannes Gäßler
|
aa374175c3
CUDA: fix crash on uneven context without FA (#16988)
|
2 ay önce |
 Georgi Gerganov
|
5b180c3d60
metal : initial Metal4 tensor API support (#16634)
|
2 ay önce |
|
Georgi Gerganov
|
b7f9010d24
server : disable checkpoints with mtmd (#17045)
|
2 ay önce |
 Xuan-Son Nguyen
|
4882f0ff78
clip: implement minicpm-v sinusoidal embd using GGML (#17036)
|
2 ay önce |
 YehuditE
|
9d7c518d64
sycl: add CONCAT operator support (#16047)
|
2 ay önce |
|
Johannes Gäßler
|
22c8c3c6ad
docs: explain CUDA 11 compilation [no ci] (#16824)
|
2 ay önce |
 l3utterfly
|
6db3d1ffe6
ggml-hexagon: graceful fallback for older socs where rpcmem_alloc2 and FASTRPC_GET_URI is unsupported (#16987)
|
2 ay önce |
 bssrdf
|
230d1169e5
improve CUDA cpy memory bandwidth when copying transposed tensor (#16841)
|
2 ay önce |
 Jeff Bolz
|
a44d77126c
vulkan: Fix GGML_VULKAN_CHECK_RESULTS to better handle fusion (#16919)
|
2 ay önce |
 Gabe Goodhart
|
5886f4f545
examples(gguf): GGUF example outputs (#17025)
|
2 ay önce |
|
Xuan-Son Nguyen
|
92bb84f775
mtmd: allow QwenVL to process larger image by default (#17020)
|
2 ay önce |
|
Georgi Gerganov
|
13b339bcd9
server : do not default to multiple slots with speculative decoding (#17017)
|
2 ay önce |
|
Xuan-Son Nguyen
|
2f0c2db43e
mtmd: improve struct initialization (#16981)
|
2 ay önce |
 손희준
|
fd2f84f468
docs: Clarify the endpoint that webui uses (#17001)
|
2 ay önce |
 Li Pengzhan
|
9f052478c2
model : add openPangu-Embedded (#16941)
|
2 ay önce |
 Reese Levine
|
03ea04175d
ggml webgpu: minor set rows optimization (#16810)
|
2 ay önce |
|
Georgi Gerganov
|
cdabeb2c27
sync : ggml
|
2 ay önce |
|
Georgi Gerganov
|
852ce5180a
ggml : fix conv2d_dw SVE path (ggml/1380)
|
2 ay önce |
 mnehete32
|
9aa63374f2
CUDA: update ops.md (#17005)
|
2 ay önce |
 lhez
|
5e90233bdb
opencl: update doc (#17011)
|
2 ay önce |
 nullname
|
a5c07dcd7b
refactor: replace sprintf with snprintf for safer string handling in dump functions (#16913)
|
2 ay önce |
|
Jeff Bolz
|
ad51c0a720
vulkan: remove the need for the dryrun (#16826)
|
2 ay önce |
|
Georgi Gerganov
|
66d8eccd42
server : do context shift only while generating (#17000)
|
2 ay önce |
|
Georgi Gerganov
|
afd353246d
readme : update hot topics (#17002)
|
2 ay önce |
 Acly
|
cc98f8d349
ggml-cpu : bicubic interpolation (#16891)
|
2 ay önce |
 Sigbjørn Skjæret
|
d945834366
ci : apply model label to models (#16994)
|
2 ay önce |
|
Sigbjørn Skjæret
|
b164259bba
chore : fix models indent after refactor (#16992)
|
2 ay önce |
 Noah
|
1f5accb8d0
Fix garbled output with REPACK at high thread counts (#16956)
|
2 ay önce |
 Aman Gupta
|
2759ccdb4a
CUDA: avoid mul + bias fusion when doing fusion (#16935)
|
2 ay önce |
