 Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
il y a 1 an |
 Neo Zhang
|
ce023f6f2f
add device version in device list (#6959)
|
il y a 1 an |
 slaren
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
il y a 1 an |
 Neo Zhang Jianyu
|
17e98d4c96
fix mul_mat_id() for new input, make the ut pass (#6682)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
de17e3f745
fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
|
il y a 1 an |
 Abhilash Majumder
|
87fb5b4234
remove row=1 cond (#6532)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
d4f220a5cc
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M (#6521)
|
il y a 1 an |
 Ouadie EL FAROUKI
|
1b496a745c
[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)
|
il y a 1 an |
 Meng, Hengyu
|
52604860f9
[SYCL] Disable iqx on windows as WA (#6435)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
25f4a613c4
[SYCL] fix set main gpu crash (#6339)
|
il y a 1 an |
 AidanBeltonS
|
e82f9e2b83
[SYCL] Fix batched impl for NVidia GPU (#6164)
|
il y a 1 an |
 compilade
|
557410b8f0
llama : greatly reduce output buffer memory usage (#6122)
|
il y a 1 an |
|
Meng, Hengyu
|
ddf6568510
[SYCL] offload op (#6217)
|
il y a 1 an |
|
AidanBeltonS
|
c5b8595e3f
Add nvidia and amd backends (#6157)
|
il y a 1 an |
|
slaren
|
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
46acb36767
fix set main gpu error (#6073)
|
il y a 1 an |
|
AidanBeltonS
|
753e36f650
[SYCL] Fix non-intel device selection (#6042)
|
il y a 1 an |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
il y a 1 an |
|
AidanBeltonS
|
b3d978600f
Update get version (#6025)
|
il y a 1 an |
|
Georgi Gerganov
|
8030da7afe
ggml : reuse quantum structs across backends (#5943)
|
il y a 1 an |
|
Georgi Gerganov
|
48358b2e5b
sycl : update IQ1_S kernels (WIP - not working!) (#5995)
|
il y a 1 an |
|
Abhilash Majumder
|
ef3ced26a3
[SYCL] Add q3_s and q1_s (#5886)
|
il y a 1 an |
|
Georgi Gerganov
|
8a3012a4ad
ggml : add ggml-common.h to deduplicate shared code (#5940)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
89fb735fcf
Revert "[SYCL] fix error when set main gpu to non-zero (#5901)" (#5918)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
ceca1aef07
[SYCL] fix error when set main gpu to non-zero (#5901)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
8ced9f7e32
add wait() to make code stable (#5895)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
21b0867433
[SYCL] fix mul_mat fault in CI/unit-test (#5862)
|
il y a 1 an |
 Michael Podvitskiy
|
9fa2627347
ggml : introduce ggml_status (ggml/750)
|
il y a 1 an |
|
Neo Zhang Jianyu
|
715641391d
Support multiple GPUs (split mode) on SYCL backend (#5806)
|
il y a 1 an |
|
AidanBeltonS
|
38d1521608
[SYCL] Use batched mul_mat pathway (#5591)
|
il y a 1 an |
