b2885

metal : support FA without mask + add asserts (#7278)

* ggml : fa without mask + add asserts

ggml-ci

* metal : support non-contiguous KV

ggml-ci

b2884

sync : ggml

ggml-ci

b2879

server: free sampling contexts on exit (#7264)

* server: free sampling contexts on exit

This cleans up last leak found by the address sanitizer.

* fix whitespace

* fix whitespace

b2878

Revert "move ndk code to a new library (#6951)" (#7282)

This reverts commit efc8f767c8c8c749a245dd96ad4e2f37c164b54c.

b2877

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

b2876

llama : disable pipeline parallelism with nkvo (#7265)

b2875

move ndk code to a new library (#6951)

b2874

Add left recursion check: quit early instead of going into an infinit…

…e loop (#7083)

* Add left recursion check: quit early instead of going into an infinite loop

* Remove custom enum, rename left recursion check and move to "grammar internal" section, add handling for edge case where a leftmost nonterminal may be empty

* Remove unnecessary declaration

b2871

llama : less KV padding when FA is off (#7257)

ggml-ci

b2870

llava-cli: fix base64 prompt (#7248)