thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

ci : check that pre-tokenizer hashes are up-to-date (#15032)

Browse source 
* torch is not required for convert_hf_to_gguf_update

* add --check-missing parameter

* check that pre-tokenizer hashes are up-to-date
This commit is contained in:
Sigbjørn Skjæret 2025-08-02 14:39:01 +02:00 • committed by GitHub
parent 711d5e6fe6
commit 2bf3fbf0b5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 60 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

6
requirements/requirements-convert_hf_to_gguf_update.txt
View file

@ -1,7 +1 @@
-r ./requirements-convert_legacy_llama.txt
--extra-index-url https://download.pytorch.org/whl/cpu
torch~=2.2.1; platform_machine != "s390x"
# torch s390x packages can only be found from nightly builds
--extra-index-url https://download.pytorch.org/whl/nightly
torch>=0.0.0.dev0; platform_machine == "s390x"