Francis Couture-Harpin 8d61607656 ggml ; remove unused ggml_mul special case ...

It would otherwise conflict with the more general
optimization coming with Mamba-2.

* ggml : handle TQ1_0 and TQ2_0 in dequantization-based operators

2024-09-04 13:50:08 -04:00

..

ggml-cann

ggml : move rope type enum to ggml.h (#8949)

2024-08-13 21:13:15 +02:00

ggml-cuda

sync : ggml

2024-08-27 22:41:27 +03:00

ggml-sycl

[SYCL] Fix DMMV dequantization (#9279)

2024-09-04 16:26:33 +01:00

kompute @ 4565194ed7

…

kompute-shaders

ggml : move rope type enum to ggml.h (#8949)

2024-08-13 21:13:15 +02:00

llamafile

sgemm : improved Q4_0 and Q8_0 performance via 4xN and Mx4 gemm (#8908)

2024-08-31 11:20:35 +03:00

vulkan-shaders

vulkan : fix build (#0)

2024-08-27 22:41:27 +03:00

CMakeLists.txt

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

ggml-aarch64.c

ggml : AVX2 support for Q4_0_8_8 (#8713)

2024-09-04 19:51:22 +03:00

ggml-aarch64.h

ggml : minor naming changes (#8433)

2024-07-12 10:46:02 +03:00

ggml-alloc.c

ggml : reduce hash table reset cost (#8698)

2024-07-27 04:41:55 +02:00

ggml-backend-impl.h

…

ggml-backend.c

Threadpool: take 2 (#8672)

2024-08-30 01:20:53 +02:00

ggml-blas.cpp

ggml : reduce hash table reset cost (#8698)

2024-07-27 04:41:55 +02:00

ggml-cann.cpp

[CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871)

2024-08-06 12:42:42 +08:00

ggml-common.h

ggml-quants : rename fields of TQ1_0 and TQ2_0 structs for consistency

2024-08-03 16:22:04 -04:00

ggml-cuda.cu

sync : ggml

2024-08-27 22:41:27 +03:00

ggml-impl.h

Merge branch 'master' into compilade/bitnet-ternary

2024-08-11 15:52:29 -04:00

ggml-kompute.cpp

ggml : reduce hash table reset cost (#8698)

2024-07-27 04:41:55 +02:00

ggml-metal.m

sync : ggml

2024-08-27 22:41:27 +03:00

ggml-metal.metal

sync : ggml

2024-08-27 22:41:27 +03:00

ggml-quants.c

Merge branch 'master' into compilade/bitnet-ternary

2024-09-04 13:26:50 -04:00

ggml-quants.h

Merge branch 'master' into compilade/bitnet-ternary

2024-08-11 15:52:29 -04:00

ggml-rpc.cpp

rpc : print error message when failed to connect endpoint (#9042)

2024-08-19 10:11:45 +03:00

ggml-sycl.cpp

[SYCL] Add oneDNN primitive support (#9091)

2024-08-22 12:50:10 +08:00

ggml-vulkan.cpp

sync : ggml

2024-08-27 22:41:27 +03:00

ggml.c

ggml ; remove unused ggml_mul special case

2024-09-04 13:50:08 -04:00