 Radoslav Gerganov
|
afd9909a64
rpc : backend refactoring (#9912)
|
пре 1 година |
 Ouadie EL FAROUKI
|
87421a23e8
[SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705)
|
пре 1 година |
 Ma Mingfei
|
60ce97c9d8
add amx kernel for gemm (#8998)
|
пре 1 година |
 Georgi Gerganov
|
8901755ba3
server : add n_indent parameter for line indentation requirement (#9929)
|
пре 1 година |
 Daniel Bevenius
|
6f55bccbb8
llama : rename batch_all to batch (#8881)
|
пре 1 година |
|
Georgi Gerganov
|
17bb928080
readme : remove --memory-f32 references (#9925)
|
пре 1 година |
|
Georgi Gerganov
|
9f45fc1e99
llama : change warning to debug log
|
пре 1 година |
|
Georgi Gerganov
|
99bd4ac28c
llama : infill sampling handle very long tokens (#9924)
|
пре 1 година |
 Tim Wang
|
3752217ed5
readme : update bindings list (#9918)
|
пре 1 година |
 Diego Devesa
|
f010b77a37
vulkan : add backend registry / device interfaces (#9721)
|
пре 1 година |
 Gilad S.
|
2194200278
fix: allocating CPU buffer with size `0` (#9917)
|
пре 1 година |
|
Gilad S.
|
73afe681aa
fix: use `vm_allocate` to allocate CPU backend buffer on macOS (#9875)
|
пре 1 година |
|
Daniel Bevenius
|
9e04102448
llama : suppress conversion from 'size_t' to 'int' (#9046)
|
пре 1 година |
|
Daniel Bevenius
|
dbf18e4de9
llava : fix typo in error message [no ci] (#9884)
|
пре 1 година |
 Joe Eli McIlvain
|
66c2c93082
grammar : fix JSON Schema for string regex with top-level alt. (#9903)
|
пре 1 година |
 Molly Sophia
|
10433e8b45
llama : add tensor name for "result_norm" (#9907)
|
пре 1 година |
 Alexey Parfenov
|
1f66b699c4
server : fix the disappearance of the end of the text (#9867)
|
пре 1 година |
|
Georgi Gerganov
|
0e41b300ed
sync : ggml
|
пре 1 година |
|
Daniel Bevenius
|
cd60b88bf7
ggml-alloc : remove buffer_id from leaf_alloc (ggml/987)
|
пре 1 година |
 leo-pony
|
becfd387f6
[CANN] Fix cann compilation error (#9891)
|
пре 1 година |
|
Georgi Gerganov
|
755a9b2bf0
llama : add infill sampler (#9896)
|
пре 1 година |
|
Georgi Gerganov
|
223c25a72f
server : improve infill context reuse (#9894)
|
пре 1 година |
 MaggotHATE
|
fbc98b748e
sampling : add XTC sampler (#9742)
|
пре 1 година |
|
Georgi Gerganov
|
dcdd535302
server : update preact (#9895)
|
пре 1 година |
 Michał Tuszyński
|
4c42f93b22
readme : update bindings list (#9889)
|
пре 1 година |
 VoidIsVoid
|
a89f75e1b7
server : handle "logprobs" field with false value (#9871)
|
пре 1 година |
 agray3
|
13dca2a54a
Vectorize load instructions in dmmv f16 CUDA kernel (#9816)
|
пре 1 година |
|
Georgi Gerganov
|
d4c19c0f5c
server : accept extra_context for the infill endpoint (#9874)
|
пре 1 година |
|
Georgi Gerganov
|
c7181bd294
server : reuse cached context chunks (#9866)
|
пре 1 година |
|
Georgi Gerganov
|
92be9f1216
flake.lock: Update (#9870)
|
пре 1 година |
