]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)
authorDavid Huang <redacted>
Mon, 3 Mar 2025 21:10:54 +0000 (05:10 +0800)
committerGitHub <redacted>
Mon, 3 Mar 2025 21:10:54 +0000 (22:10 +0100)
commitbecade5de77674696539163dfbaf5c041a1a8e97
treee4fd7306fd74716364ef3e3beb5b036530f83df2
parentdfd6b2c0be191b3abe2fd9c1b25deff01c6249d8
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)

Adds GGML_HIP_ROCWMMA_FATTN and rocwmma header check
Adds rocWMMA support to fattn-wmma-f16

---

Signed-off-by: Carl Klemm <redacted>
Co-authored-by: Johannes Gäßler <redacted>
Co-authored-by: Ben Jackson <redacted>
ggml/CMakeLists.txt
ggml/src/ggml-cuda/common.cuh
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/fattn-wmma-f16.cu
ggml/src/ggml-cuda/fattn.cu
ggml/src/ggml-hip/CMakeLists.txt