Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)
0bcd751
Christian Kastner
Diego Devesa
commited on
Spaces:
Running
Running
Commit History
ggml : fix repack work size for mul_mat_id (llama/14292)
4b0d2de
ggml: Update KleidiAI to v1.9.0 (llama/14277)
90ccf35
Charles Xu
commited on
ggml-cpu : remove unnecesary arm feature detection (llama/14281)
62cf694
Diego Devesa
commited on
llamafile : support s390x SIMD instruction set (llama/14273)
26bafb6
ggml-cpu: reduce asm calls for hsum (llama/14037)
17c0dfa
ggml-cpu: fix uncaught underscore terminators (llama/14023)
c005248
ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)
9d1d21b
Charles Xu
commited on
Add `ggml_roll` (ggml/1274)
71923e5
ggml-cpu : remove the weak alias trick (llama/14221)
a1bcb29
xctan
commited on
llama : add thread safety test (llama/14035)
acc9311
ggml: Add Android support for GGML_CPU_ALL_VARIANTS (llama/14206)
7ddd89c
Charles Xu
commited on
ggml-cpu : rework weak alias on apple targets (llama/14146)
de5e986
xctan
commited on
Implement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)
c9cec9d
Christian Kastner
commited on
ggml : fix weak alias win32 (#0)
d47070d
files : remove old sources (part 2)
c1c9908
files : remove old sources
e4ae8c6
ggml-cpu : split arch-specific implementations (llama/13892)
8c833e9
releases : use dl backend for linux release, remove arm64 linux release (llama/13996)
9896625
Diego Devesa
commited on
cmake : Handle mixed-case 'Power' strings in POWER CPU detection (llama/13966)
bc1415b
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)
d5d55f2
Max Krasnyansky
Diego Devesa
commited on
arm64: optimize q4_k_q8_k kernel with i8mm (llama/13886)
026ea5b
Yibo Cai
commited on
cmake: Factor out CPU architecture detection (llama/13883)
b436dcc
Christian Kastner
commited on
ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (llama/13882)
bfc960a
ggml: aarch64: Implement SVE F32 kernels for vector functions (llama/13843)
7941e9b
Vineel Abhinav
commited on
ggml : riscv: add xtheadvector support (llama/13720)
4790d5d
xctan
commited on
ggml-cpu: x86 feature detection is specific to x86 (llama/13811)
d86ba47
Christian Kastner
commited on
ggml-cpu : set openmp wait time if not set (llama/13758)
276d920
Diego Devesa
commited on
ggml : add ggml_gelu_erf() (llama/13667)
6c9cd9a
arm64: optimize q6_k_q8_k kernel with i8mm (llama/13519)
03048ea
Yibo Cai
commited on
ggml-cpu: Update KleidiAI to v1.6 and fix include directives (llama/13509)
7463545
Dan Johansson
commited on
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel (llama/13053)
0612f1f
Dan Johansson
Charles Xu
commited on
rpc : use backend registry, support dl backends (llama/13304)
0286805
Diego Devesa
commited on
ggml : activate s390x simd for Q3_K (llama/13301)
1bfe279
ggml : Enable MMA for BF16 in llamafile_sgemm (llama/13148)
7da5bcc
whisper: remove MSVC warnings pragmas (#3090)
e0d130c
unverified
ggml : fix ppc64le build (llama/13176)
07ec79f
feat(ggml-cpu): enable z17 compile (llama/13182)
10f7d18
Aaron Teo
commited on
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (llama/13107)
c47823e
ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (llama/12871)
f8795d3
Diego Devesa
commited on
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (llama/12829)
2457b99
Srihari-mcw
commited on
ggml : Depthwise 2D convolution (ggml/1152)
0c950d5
ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly accumulate into the result register (llama/12773)
acb674d
ggml: fix compilation error s390x (llama/12848)
2458d68
Aaron Teo
Aleksei Nikiforov
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
Fixes #12823 (llama/12830)
8a74c6b
ggml-cpu-impl.h: do not redefine bool on POWER9 (llama/12856)
bb47d22
Piotr Kubaj
commited on
llama : fix FA when KV cache is not used (i.e. embeddings) (llama/12825)
e7cb2dc
ggml : add bilinear upscale support (ggml/1185)
4c5e449
Diego Devesa
commited on
ggml : add more generic custom op, remove deprecated custom ops (ggml/1183)
ba7a5f8
Diego Devesa
commited on