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

Skip to content

Tags: tobi/llama.cpp

Tags

master-f121705

Toggle master-f121705's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
CI: fix subdirectory path globbing (ggml-org#546)

- Changes in subdirectories will now be detecter properly
- (Windows-MSVC) AVX512 tests temporarily disabled

master-d502bc7

Toggle master-d502bc7's commit message

Verified

This commit was signed with the committer’s verified signature.
ggerganov Georgi Gerganov
tests : free llama context at the end of the test

master-d0aaff5

Toggle master-d0aaff5's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
py : add temporary script to convert old ggml files to newer version (g…

…gml-org#539)

Co-authored-by: Jakub Horak <[email protected]>

master-c1f8850

Toggle master-c1f8850's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
ggml : introduce structs for the q4 data blocks (ggml-org#356)

* Introduce structs for the q4 data blocks

* ggml : rename quant struct variables + fix ARM_NEON

---------

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

master-a6bdc47

Toggle master-a6bdc47's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
Fix usage of F16C intrinsics in AVX code (ggml-org#563)

* Fix usage of F16C intrinsics in AVX code when F16C is not defined

master-436e561

Toggle master-436e561's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
all : be more strict about converting float to double (ggml-org#458)

* Be more strict about converting float to double

* Test equivalence of round, SILU implementations

Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.

* Fix softmax in perplexity.cpp

* all : prefer float over double where appropriate

* perplexity : add <cmath>

---------

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

master-99c5b27

Toggle master-99c5b27's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
ggml : refactor quantized processing functions (ggml-org#509)

* Refactor quantized processing functions

* ggml : minor

---------

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

master-96f9c05

Toggle master-96f9c05's commit message

Verified

This commit was signed with the committer’s verified signature.
ggerganov Georgi Gerganov
ci : make ctest verbose, hopefully we see what is wrong with the sani…

…tizer

master-20e1e84

Toggle master-20e1e84's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
deploy : add a Package.swift for SwiftPM support (ggml-org#393)

* Add a Package.swift for SwiftPM support

* Swap from exclusions to allowlist

master-7f4c5c6

Toggle master-7f4c5c6's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
llama : fix linkage with mingw (ggml-org#551)

* Revert 7e53955 (ggml-org#542)

Still needs to be fixed properly

* Fix linking on mingw32