关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
thomas-yanxin
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
Not watched
1
1
Fork 0
Code
Releases 1834 Wiki Activity
Issues 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
2902 Commits
233 Branches
175 MiB
21 Download
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
llama.cpp/scripts
Georgi Gerganov 29499bb593
sync : ggml 		1 day ago
..
LlamaConfig.cmake.in cuda : rename build flag to LLAMA_CUDA (#6299) 1 month ago
build-info.cmake cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970) 5 months ago
build-info.sh build : link against build info instead of compiling against it (#3879) 6 months ago
check-requirements.sh llama : fix BPE pre-tokenization (#6920) 2 weeks ago
ci-run.sh ci : add model tests + script wrapper (#4586) 3 months ago
compare-commits.sh ggml : group all experts in a single ggml_mul_mat_id (#6505) 4 weeks ago
compare-llama-bench.py llama-bench : add pp+tg test type (#7199) 6 days ago
convert-gg.sh scripts : helper convert script 8 months ago
debug-test.sh Scripting & documenting debugging one test without anything else in the loop. (#7096) 5 days ago
gen-authors.sh license : update copyright notice + add AUTHORS (#6405) 1 month ago
gen-build-info-cpp.cmake cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970) 5 months ago
gen-unicode-data.py llama3 custom regex split (#6965) 1 week ago
get-flags.mk build : pass all warning flags to nvcc via -Xcompiler (#5570) 2 months ago
get-hellaswag.sh scripts : add get-winogrande.sh 3 months ago
get-pg.sh scripts : improve get-pg.sh (#4838) 4 months ago
get-wikitext-2.sh model: support arch `DbrxForCausalLM` (#6515) 1 month ago
get-wikitext-103.sh lookup: complement data from context with general text statistics (#5479) 1 month ago
get-winogrande.sh scripts : add get-winogrande.sh 3 months ago
hf.sh scripts : add --outdir option to hf.sh (#6600) 1 month ago
install-oneapi.bat support SYCL backend windows build (#5208) 3 months ago
pod-llama.sh cuda : rename build flag to LLAMA_CUDA (#6299) 1 month ago
qnt-all.sh scripts : add pipefail 8 months ago
run-all-perf.sh scripts : add pipefail 8 months ago
run-all-ppl.sh scripts : add pipefail 8 months ago
run-with-preset.py convert.py : add python logging instead of print() (#6511) 1 week ago
server-llm.sh cuda : rename build flag to LLAMA_CUDA (#6299) 1 month ago
sync-ggml-am.sh script : sync ggml-rpc 2 days ago
sync-ggml.last sync : ggml 1 day ago
sync-ggml.sh script : sync ggml-rpc 2 days ago
verify-checksum-models.py convert.py : add python logging instead of print() (#6511) 1 week ago
xxd.cmake `build`: generate hex dump of server assets during build (#6661) 3 weeks ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

C++ C Cuda Python Metal other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit