whisper.cpp / ggml.h

Commit History

SOTA 3-bit quants (llama/5196)
4649943
unverified

Kawrakow ikawrakow commited on

ggml : add unified SYCL backend for Intel GPUs (llama/2690)
01169e0
unverified

Abhilash Majumder jianyuzh KevinLy hengyu ggerganov commited on

minor : clean-up some warnings and style (llama/5094)
7df090b
unverified

ggerganov commited on

llava : MobileVLM support (llama/4954)
dc8f956
unverified

cxt123 Chenxiaotao03 commited on

ggml : add IQ2 to test-backend-ops + refactoring (llama/4990)
227f2ae
unverified

ggerganov commited on

imatrix : offload to GPU support (llama/4957)
6490f98
unverified

ggerganov commited on

ggml : introduce GGML_CALL function annotation (llama/4850)
7815f68
unverified

jartine commited on

2-bit quantizations (llama/4897)
8a399ab
unverified

Kawrakow ikawrakow commited on

Importance Matrix calculation (llama/4861)
c0b17f1
unverified

Kawrakow ikawrakow ggerganov commited on

ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)
5e827d5
unverified

Kawrakow ikawrakow commited on

ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693)
6469bfe
unverified

Timothy Cronin commited on

ggml : change GGML_MAX_NAME at compile time (ggml/682)
ded2b1a
unverified

leejet commited on

SOTA 2-bit quants (llama/4773)
75de5bf
unverified

Kawrakow ikawrakow commited on

ggml : add ggml_cpu_has_avx_vnni() (llama/4589)
b10cbfd

alandao ggerganov commited on

sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)
919a447
unverified

ggerganov commited on

sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
aa86ade
unverified

ggerganov commited on

sync : ggml (Metal fixes, new ops, tests) (#1633)
a0d4b48
unverified

ggerganov commited on

sync : ggml (new ops, new backend, etc) (#1602)
895e87a
unverified

ggerganov commited on

sync : ggml (ggml-alloc + linker + gguf fixes) (#1501)
58507b9
unverified

ggerganov commited on

whisper : add full CUDA and Metal offloading (#1472)
da4acca
unverified

ggerganov commited on

sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified

ggerganov Chris Raethke commited on

sync : ggml (const correctness)
4ce2d25
unverified

ggerganov commited on

metal : add F32 support + update bench output
02d7878
unverified

ggerganov commited on

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247)
8bb66c1
unverified

ggerganov commited on

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)
d41ba35
unverified

ggerganov commited on

ggml : detect SSSE3 (#1211)
82a619c
unverified

Przemysław Pawełczyk commited on

ggml : sync latest repo (mostly refactoring changes)
d97fd69
unverified

ggerganov commited on

ggml : sync latest ggml lib
a100c9a
unverified

ggerganov commited on

ggml : sync latest ggml repo
6ee8740
unverified

ggerganov commited on

ggml : sync latest ggml
803e1be
unverified

ggerganov commited on

ggml : sync ggml (clBLAST + tensor names)
f50d3b3
unverified

ggerganov commited on

whisper : add integer quantization support (#540)
a5f8f3c
unverified

ggerganov commited on

ggml : sync with ggml repo (warning fixes + asserts)
caf2759
unverified

ggerganov commited on

ggml : sync latest ggml + llama.cpp updates (quantization)
ede1268
unverified

ggerganov commited on

ggml : sync latest ggml
7b8292f
unverified

ggerganov commited on

ggml : sync latest changes from ggml and llama.cpp
3bd52ce
unverified

ggerganov commited on

ggml : backport llama.cpp updates (close #709)
bf6b4f8
unverified

ggerganov commited on

talk-llama : add new example + sync ggml from llama.cpp (#664)
a8c74e6
unverified

ggerganov commited on

whisper : reduce memory usage during inference (#431)
3aa9e6c
unverified

ggerganov commited on

ggml : add SSE3 and fp16 conversion lookup table (#368)
2c3f7d4
unverified

Abitofevrything ggerganov commited on

whisper : document POWER VSX support
4dbf7ee

Thomas Fitzsimmons commited on

ggml : simplify the SIMD code (#324)
6fe850c
unverified

ggerganov commited on

Check for both __ARM_NEON and __ARM_FEATURE_FMA so that the project can be compiled for armv7a.
1fff54f

Kevin Brothaler commited on

ggml : make more compatible with c99 (#262)
52bc68d
unverified

ggerganov commited on

ggml : add F16C CPU flag check
2661c19
unverified

ggerganov commited on

add AVX support
00ac035

katsu560 commited on

ref #40 : start working on the documentation
7ef045e
unverified

ggerganov commited on

parallel : working
d5d2d41

ggerganov commited on