Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Tags: shards-lang/llama.cpp

Tags

shards-1

Toggle shards-1's commit message

b4679

Toggle b4679's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge branch 'ggerganov:master' into master

b4293

Toggle b4293's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
vulkan: fix compile warnings (ggml-org#10731)

b4292

Toggle b4292's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
cmake : simplify msvc charsets (ggml-org#10672)

b4291

Toggle b4291's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : fix format_infill (ggml-org#10724)

* server : fix format_infill

* fix

* rename

* update test

* use another model

* update test

* update test

* test_invalid_input_extra_req

b4290

Toggle b4290's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : bring back info of final chunk in stream mode (ggml-org#10722)

* server : bring back into to final chunk in stream mode

* clarify a bit

* traling space

b4288

Toggle b4288's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
llama : use cmake for swift build (ggml-org#10525)

* llama : use cmake for swift build

* swift : <> -> ""

* ci : remove make

* ci : disable ios build

* Revert "swift : <> -> """

This reverts commit d39ffd9.

* ci : try fix ios build

* ci : cont

* ci : cont

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b4287

Toggle b4287's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
vulkan: compile a test shader in cmake to check for coopmat2 support (g…

…gml-org#10713)

b4285

Toggle b4285's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
server : (refactor) no more json in server_task input (ggml-org#10691)

* server : (refactor) no more json in server_task input

* add test for slots endpoint

* add tests for /props and /slots

* remove task inf_type

* fix CI by adding safe_json_to_str

* add "model_path" to /props

* update readme

b4284

Toggle b4284's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
ggml : disable iq4_nl interleave size 8 (ggml-org#10709)

ggml-ci