llama.cpp
5a32a9b8 - Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (#20507)

Commit

33 days ago

Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (#20507) * Fix datarace in CUDA's "cpy" kernel. * Remove extra barrier by using more of shared memory.

References

#20507 - Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations).

Author

Exile333

Parents

3b439504

llama.cpp 5a32a9b8 - Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (#20507)

llama.cpp
5a32a9b8 - Fix data race in CUDA's "cpy" kernel (influences GGML's DUP, CONT operations). (#20507)