]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 31afcbe)
ggml : x2 speed for WASM by optimizing SIMD (#11453)
authorXuan-Son Nguyen <redacted>
Wed, 12 Feb 2025 23:33:45 +0000 (00:33 +0100)
committerGitHub <redacted>
Wed, 12 Feb 2025 23:33:45 +0000 (00:33 +0100)
commitbe3bbd62153820ff6d358c817360927f429105c4
tree0ed3d331113cc3cb586bf03980082aafc3ee36catree
parent31afcbee0eebbc998ab311aa314e389d60aa2127commit | diff
ggml : x2 speed for WASM by optimizing SIMD (#11453)

* ggml : x2 speed for WASM by optimizing SIMD

* fix bad merging

* rm trailing spaces

* rm redundant clamp

* better quantize_row_q8_K

Co-authored-by: camel-cdr <redacted>
* remove memset that causes buffer overflow
Co-authored-by: camel-cdr <redacted>
---------

Co-authored-by: camel-cdr <redacted>
ggml/src/ggml-cpu/ggml-cpu-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp