ggml : fix field name when new ggml_backend (llama/14944)
685748d
AN Long
commited on
Spaces:
Running
Running
Commit History
ggml : fix fallback to CPU for ununsupported ops (llama/15118)
2b7ae5e
Diego Devesa
commited on
ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)
fea8f94
ggml-cpu : split arch-specific implementations (llama/13892)
8c833e9
rpc : use backend registry, support dl backends (llama/13304)
0286805
Diego Devesa
commited on
cpu: fix cpu backend's supports-op for GET_ROWS_BACK. fixes a fatal when running test-backend-ops with only the CPU backend (ggml/1190)
ee7706c
cmdr2
commited on
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)
05466a9
Rémy O
commited on
ggml-cpu: Support s390x SIMD Instruction Set (llama/12019)
4aa54ec
Aaron Teo
Jinyang He
junchao-zhao
commited on
ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390)
9de6d81
Charles Xu
commited on
ggml-cpu: Fix duplicate MATMUL_INT8 (llama/11817)
05b9e78
Fix #11802: Compile bug - RegQueryValueExA changed to RegQueryValueEx (llama/11803)
86969ac
Sheldon Robinson
commited on
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380)
855a9fe
CUDA: backwards pass for misc. ops, add tests (llama/11257)
2fbcec1
RoPE: fix back, CUDA support for back + noncont. (llama/11240)
131a21e
ggml : fix arm build (llama/10890)
e58e7a9
Diego Devesa
Adrien Gallouët
commited on
ggml : update ggml_backend_cpu_device_supports_op (llama/10867)
2f11d1e
ggml : refactor online repacking (llama/10446)
163128e
ggml : add predefined list of CPU backend variants to build (llama/10626)
1794b43
Diego Devesa
commited on
ggml : move AMX to the CPU backend (llama/10570)
3732429
Diego Devesa
commited on
ggml-cpu: support IQ4_NL_4_4 by runtime repack (llama/10541)
bf73242
ggml : add support for dynamic loading of backends (llama/10469)
b73266f
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (llama/9921)
3541ee8
Charles Xu
Diego Devesa
commited on