]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 784e11d)
quantize : add '--keep-split' to quantize model into shards (#6688)
authorjiez <redacted>
Thu, 25 Apr 2024 10:29:35 +0000 (18:29 +0800)
committerGitHub <redacted>
Thu, 25 Apr 2024 10:29:35 +0000 (13:29 +0300)
commit1966eb2615242f224bf9ca939db8905ab6a174a0
tree3da33a1b5f816723e195a4936d44c4bef2eaa06atree
parent784e11dea1f5ce9638851b2b0dddb107e2a609c8commit | diff
quantize : add '--keep-split' to quantize model into shards (#6688)

* Implement '--keep-split' to quantize model into several shards

* Add test script

* Update examples/quantize/quantize.cpp

Co-authored-by: Georgi Gerganov <redacted>
* Split model correctly even if tensor id is out-of-order

* Update llama_model_quantize_params

* Fix preci failures

---------

Co-authored-by: z5269887 <redacted>
Co-authored-by: Georgi Gerganov <redacted>
examples/quantize/quantize.cpp diff | blob | history
examples/quantize/test.sh [new file with mode: 0644] blob
llama.cpp diff | blob | history
llama.h diff | blob | history
Packaging of ggml-org/llama.cpp