llama.cpp
a5bb8ba4 - CUDA: tune GLM 4.7 Flash FA kernel selection logic (#19097)

Commit

11 hours ago

CUDA: tune GLM 4.7 Flash FA kernel selection logic (#19097)

References

#19097 - CUDA: tune GLM 4.7 Flash FA kernel selection logic

Author

JohannesGaessler

JohannesGaessler

Parents

Loading