llama.cpp
b70d2510 - CUDA: add gqa_ratio 4 for GLM 4.7 flash (#18953)

Commit

48 days ago

CUDA: add gqa_ratio 4 for GLM 4.7 flash (#18953)

References

#18953 - CUDA: add gqa_ratio 4 for GLM 4.7 flash

Author

am17an

am17an

Parents

Loading