Hugging Face's logo

Spaces:
natasa365
/
whisper.cpp
Sleeping

App Files Community
whisper.cpp / ggml-quants.c

Commit History

ggml : introduce bfloat16 support (llama/6412)
81ec961

Justine Tunney commited on

add basic tensor data validation function (llama/6884)
71e001c

slaren commited on

ggml : fix MIN / MAX macros (llama/6904)
a1c0e2a

ggerganov commited on

ggml : move 32-bit arm compat in ggml-impl.h (llama/6865)
7343760

ggerganov commited on

ggml : add llamafile sgemm (llama/6414)
093eec4

Justine Tunney commited on

build: fix and ignore msvc warnings (ggml/805)
c40b574

stanimirovb commited on

llama : add Command R Plus support (llama/6491)
8cf7097
unverified

Carolinabanana S S slaren ggerganov commited on

sync : ggml (#2001)
cbbfa9e
unverified

ggerganov commited on

ggml : reuse quantum structs across backends (llama/5943)
bb0625f
unverified

ggerganov commited on

ggml : fix UB in IQ2_S and IQ3_S (llama/6012)
0c552df
unverified

ggerganov commited on

1.5 bit: we can do even better (llama/5999)
36cc71e
unverified

Kawrakow ikawrakow commited on

ggml, ci : Windows ARM runner and build fixes (llama/5979)
507b9dd
unverified

Michael Podvitskiy commited on

Better 1.5 bit quantization (llama/5971)
f3a62cc
unverified

Kawrakow ikawrakow commited on

ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (llama/5951)
cb8bbaa
unverified

ggerganov commited on

ggml : remove old quantization functions (llama/5942)
11a2545
unverified

ggerganov commited on

ggml : add ggml-common.h to deduplicate shared code (llama/5940)
0a37735
unverified

ggerganov commited on

ggml : try fix 32-bit arm compat (#1938)
6ea3354
unverified

ggerganov commited on

ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u8` (llama/5894)
7f5bc53
unverified

bobqianic commited on

quants : use MM256_SET_M128I consistently to fix gcc 7 build (llama/5889)
cdd783a
unverified

Cebtenzzre commited on

ggml : fix IQ3_S AVX implementation (llama/5834)
98e5c63
unverified

ggerganov commited on

ggml : IQ3_S improvements (llama/5829)
06a8e30
unverified

Kawrakow ikawrakow commited on

ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (llama/5760)
9a07f42
unverified

Kawrakow ikawrakow commited on

Attempt to fix android build (llama/5752)
e720b3b
unverified

Kawrakow ikawrakow commited on

IQ4_XS: a 4.25 bpw quantization (llama/5747)
0ee1bfb
unverified

Kawrakow ikawrakow commited on

ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (llama/5742)
72e8610
unverified

Engininja2 commited on

Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (llama/5721)
2b9bb9e
unverified

Kawrakow ikawrakow ggerganov commited on

ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (llama/5711)
430efc6
unverified

Crad commited on

IQ3_S: a much better alternative to Q3_K (llama/5676)
32589c9
unverified

Kawrakow ikawrakow commited on

ggml : always define ggml_fp16_t as uint16_t (llama/5666)
bc567d3
unverified

ggerganov commited on

ggml : 32-bit arm compat (#1891)
7551157
unverified

ggerganov commited on

sync : llama.cpp (ggml/0)
f8e8d34
unverified

ggerganov commited on

ggml : restore vec dot stride arg names (llama/5453)
de4041f
unverified

ggerganov commited on

ci : fix wikitext url + compile warnings (llama/5569)
49f0106
unverified

ggerganov commited on

1.5 bit quantization (llama/5453)
9c3aa6a
unverified

Kawrakow ikawrakow commited on

ggml-quants : fix compiler warnings (shadow variable) (llama/5472)
e538f25
unverified

Kawrakow ikawrakow commited on

ggml : fix compile warnings (unused vars) (llama/4966)
97fa2e3
unverified

ggerganov commited on

ggml : add mmla kernels for quantized GEMM (llama/4966)
0d50a29
unverified

snadampal commited on

ggml : fix `error C2078: too many initializers` for MSVC ARM64 (llama/5404)
8ebb36c
unverified

Michael Podvitskiy commited on

Slight quantization improvement for Q4_K and Q5_K (llama/5361)
e3cd020
unverified

Kawrakow ikawrakow commited on

iq2_xxs: tune quantization (llama/5320)
11e5f6b
unverified

Kawrakow ikawrakow commited on

Faster AVX2 dot product for IQ2_XS (llama/5187)
187ae44
unverified

Kawrakow ikawrakow PeterReid commited on

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

Kawrakow ikawrakow commited on

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

ggerganov commited on

ggml : importance matrix support for legacy quants (llama/4969)
d8bb9d8
unverified

Kawrakow ikawrakow commited on

Add ability to use importance matrix for all k-quants (llama/4930)
7032309
unverified

Kawrakow ikawrakow commited on

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

Kawrakow ikawrakow commited on

ggml : fix 32-bit ARM compat for IQ2_XS (#1758)
d5836c9
unverified

ggerganov commited on

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

Kawrakow ikawrakow commited on

ggml : fix vld1q_s8_x4 32-bit compat (llama/4828)
efed5ba
unverified

ggerganov commited on

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

Kawrakow ikawrakow commited on