Radoslav Gerganov
5e31828d3e
ggml : add RPC backend (#6829)
* ggml : add RPC backend
The RPC backend proxies all operations to a remote server which runs a
regular backend (CPU, CUDA, Metal, etc).
* set TCP_NODELAY
* add CI workflows
* Address review comments
* fix warning
* implement llama_max_devices() for RPC
* Address review comments
* Address review comments
* wrap sockfd into a struct
* implement get_alignment and get_max_size
* add get_device_memory
* fix warning
* win32 support
* add README
* readme : trim trailing whitespace
* Address review comments
* win32 fix
* Address review comments
* fix compile warnings on macos
2024-05-14 14:27:19 +03:00
..
2024-05-05 13:38:55 +02:00
2024-05-14 14:27:19 +03:00
2024-05-01 08:13:59 +03:00
2024-04-04 18:30:53 +02:00
2024-04-14 13:12:36 +02:00
2024-04-04 18:30:53 +02:00
2024-04-03 21:01:13 +03:00
2024-04-04 18:30:53 +02:00
2024-04-04 18:30:53 +02:00
2024-01-11 17:22:34 +00:00
2023-12-31 13:14:58 -08:00
2024-04-04 18:30:53 +02:00
2024-05-03 22:36:41 +03:00
2024-04-29 17:02:45 +01:00
2024-04-04 18:30:53 +02:00