Radoslav Gerganov
|
41386cf365
rpc : report actual free memory (#16616)
|
3 months ago |
Radoslav Gerganov
|
f39283960b
rpc : check src buffer when copying tensor (#16421)
|
4 months ago |
Radoslav Gerganov
|
898acba681
rpc : add support for multiple devices (#16276)
|
4 months ago |
Radoslav Gerganov
|
c498fc82fe
rpc : use ggml logging facilities
|
4 months ago |
Jeff Bolz
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 months ago |
Jeff Bolz
|
e68aa10d8f
vulkan: sort graph to allow more parallel execution (#15850)
|
5 months ago |
Tak-RS
|
e71d48e326
ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (#15188)
|
5 months ago |
AN Long
|
cd6983d56d
ggml : fix field name when new ggml_backend (#14944)
|
6 months ago |
Chris Rohlf
|
64bf1c3744
rpc : check for null buffers in get/set/copy tensor endpoints (#14868)
|
6 months ago |
Isaac McFadyen
|
2bb0467043
rpc : nicer error messages for RPC server crash (#14076)
|
8 months ago |
Radoslav Gerganov
|
b486ba05bf
rpc : add rpc_msg_set_tensor_hash_req (#13353)
|
9 months ago |
Diego Devesa
|
9fdfcdaedd
rpc : use backend registry, support dl backends (#13304)
|
9 months ago |
Justin Santa Barbara
|
8efbdadc61
rpc : avoid uninitialized memory in serialize_tensor (#13210)
|
9 months ago |
Ville Vesilehto
|
43ddab6eee
fix(rpc): Improve input validation and error handling (#13069)
|
9 months ago |
Radoslav Gerganov
|
553a5c3a9f
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)
|
9 months ago |
Radoslav Gerganov
|
2db9ba1464
rpc : add RPC_CMD_HELLO (#12955)
|
9 months ago |
Radoslav Gerganov
|
c772d54926
rpc : use ggml_context_ptr (#12938)
|
9 months ago |
Radoslav Gerganov
|
ab6ab8f809
rpc : send hash when tensor data is above some fixed threshold (#12496)
|
10 months ago |
William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
11 months ago |
Patrick Peng
|
1d20e53c40
rpc: fix known RCE in rpc-server (ggml/1103)
|
1 year ago |
Radoslav Gerganov
|
6da5bec81c
rpc : better caching of the base buffer pointer (#11331)
|
1 year ago |
Radoslav Gerganov
|
a4dd490069
rpc : code cleanup (#11107)
|
1 year ago |
matt23654
|
f922a9c542
[GGML][RPC] Support for models with non-512-aligned tensors over RPC. (#11047)
|
1 year ago |
Diego Devesa
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 year ago |
Diego Devesa
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |