EngineX-Iluvatar/enginex-bi_150-llama.cpp
15
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
3 Commits 1 Branch 1 Tag
8d3f9b9cb16a74abe7422af32847d6b76e4f740e
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
xiezhongtao 8d3f9b9cb1 fix(ggml-cuda): 修正CUDA编译标志和WARP_SIZE配置 
更新CUDA编译标志以使用正确的fast-math和extended-lambda选项
调整WARP_SIZE为64以适配目标硬件
移除-Wmissing-noreturn警告选项
修复cudaStreamWaitEvent调用缺少参数的问题
2026-01-23 16:42:43 +08:00
benches/dgx-spark
同步 b7516
2026-01-23 11:34:20 +08:00
ci
同步 b7516
2026-01-23 11:34:20 +08:00
cmake
同步 b7516
2026-01-23 11:34:20 +08:00
common
同步 b7516
2026-01-23 11:34:20 +08:00
docs
同步 b7516
2026-01-23 11:34:20 +08:00
examples
同步 b7516
2026-01-23 11:34:20 +08:00
ggml
fix(ggml-cuda): 修正CUDA编译标志和WARP_SIZE配置
2026-01-23 16:42:43 +08:00
gguf-py
同步 b7516
2026-01-23 11:34:20 +08:00
grammars
同步 b7516
2026-01-23 11:34:20 +08:00
include
同步 b7516
2026-01-23 11:34:20 +08:00
licenses
同步 b7516
2026-01-23 11:34:20 +08:00
media
同步 b7516
2026-01-23 11:34:20 +08:00
models
同步 b7516
2026-01-23 11:34:20 +08:00
pocs
同步 b7516
2026-01-23 11:34:20 +08:00
requirements
同步 b7516
2026-01-23 11:34:20 +08:00
scripts
同步 b7516
2026-01-23 11:34:20 +08:00
src
同步 b7516
2026-01-23 11:34:20 +08:00
tests
同步 b7516
2026-01-23 11:34:20 +08:00
tools
同步 b7516
2026-01-23 11:34:20 +08:00
vendor
同步 b7516
2026-01-23 11:34:20 +08:00
AGENTS.md
同步 b7516
2026-01-23 11:34:20 +08:00
AUTHORS
同步 b7516
2026-01-23 11:34:20 +08:00
build-xcframework.sh
同步 b7516
2026-01-23 11:34:20 +08:00
CMakeLists.txt
同步 b7516
2026-01-23 11:34:20 +08:00
CMakePresets.json
同步 b7516
2026-01-23 11:34:20 +08:00
CODEOWNERS
同步 b7516
2026-01-23 11:34:20 +08:00
CONTRIBUTING.md
同步 b7516
2026-01-23 11:34:20 +08:00
convert_hf_to_gguf_update.py
同步 b7516
2026-01-23 11:34:20 +08:00
convert_hf_to_gguf.py
同步 b7516
2026-01-23 11:34:20 +08:00
convert_llama_ggml_to_gguf.py
同步 b7516
2026-01-23 11:34:20 +08:00
convert_lora_to_gguf.py
同步 b7516
2026-01-23 11:34:20 +08:00
flake.lock
同步 b7516
2026-01-23 11:34:20 +08:00
flake.nix
同步 b7516
2026-01-23 11:34:20 +08:00
LICENSE
同步 b7516
2026-01-23 11:34:20 +08:00
Makefile
同步 b7516
2026-01-23 11:34:20 +08:00
mypy.ini
同步 b7516
2026-01-23 11:34:20 +08:00
poetry.lock
同步 b7516
2026-01-23 11:34:20 +08:00
pyproject.toml
同步 b7516
2026-01-23 11:34:20 +08:00
pyrightconfig.json
同步 b7516
2026-01-23 11:34:20 +08:00
README.md
fix(ggml-cuda): 修正CUDA编译标志和WARP_SIZE配置
2026-01-23 16:42:43 +08:00
requirements.txt
同步 b7516
2026-01-23 11:34:20 +08:00
SECURITY.md
同步 b7516
2026-01-23 11:34:20 +08:00

README.md

enginex-bi_150-llama.cpp

运行于【天数智芯-天垓150】算力卡的【文本生成】引擎，基于 llama.cpp (b7516) 引擎进行架构特别适配优化。

Build Docker Image

docker build -t enginex-iluvatar/iluvatar-llama.cpp:b7516-bi150 .

最新镜像：git.modelhub.org.cn:9443/enginex-iluvatar/iluvatar-llama.cpp:b7516-bi150

Description
运行于【天数智芯-天垓150】算力卡的【文本生成】引擎，基于 llama.cpp 引擎进行架构特别适配优化。
Readme MIT 26 MiB
Languages
C++ 56.1%
C 12.6%
Python 7.9%
Cuda 6.5%
HTML 4.6%
Other 12.2%