llama.cpp/ggml/src/ggml-sycl/dpct at dbe7901ca652cc8fe314e6972e3ce9cb33edf33d - llama.cpp - Millaguie: A place to fork stuff

millaguie/llama.cpp

0 Fork 0

Files

T

History

Neo Zhang 213c4a0b81 [SYCL] supprt Flash Attention for fp32/fp16/Q4/Q5/Q8 (#20190 )

* support flash-attention for fp32/fp16/Q4/Q5/Q8

* rm warining

* update for JIT

2026-03-08 12:00:07 +08:00

..

helper.hpp

[SYCL] supprt Flash Attention for fp32/fp16/Q4/Q5/Q8 (#20190 )

2026-03-08 12:00:07 +08:00