Commits · Xenobd/whisper.cpp

ggml: initial IBM zDNN backend (llama/14975)

449e1a4

taronaeo commited on Aug 15

finetune: SGD optimizer, more CLI args (llama/13873)

f585fe7

Jonathan Graehl

OccamRazor

JohannesGaessler commited on Aug 14

ggml : update `ggml_rope_multi` (llama/12665)

b4896dc

Judd

ggerganov commited on Aug 13

llama : add gpt-oss (llama/15091)

bf225d6

ggerganov

ngxson HF Staff slaren commited on Aug 5

ggml : remove old kompute, cann (skip) (#3349)

d321914
unverified

ggerganov commited on Jul 30

ggml: Add initial WebGPU backend (llama/14521)

0dd208f

Reese Levine commited on Jul 16

sync : resolve conflicts (ggml/0)

497add0

ggerganov commited on Jul 12

ggml : add ggml_scale_bias (llama/14417)

573d50a

ngxson HF Staff commited on Jul 9

CUDA: add bilinear interpolation for upscale (llama/14563)

68ded09

am17an commited on Jul 8

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445)

f798922

Sigbjørn Skjæret commited on Jul 3

ggml : fix FA mask dim 2 and 3 (llama/14505)

a89dc81

ggerganov commited on Jul 3

llama : initial Mamba-2 support (llama/9126)

1b4087e

compilade commited on Jul 2

ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (llama/14435)

ebacb3e

ggerganov commited on Jul 12

ggml : Callback before abort (llama/14481)

ccee17d

Bytealyzer Diego Devesa commited on Jul 2

ggml : add version function to get lib version (ggml/1286)

880f633

danbev

ggerganov commited on Jul 2

Add Conv2d for CPU (llama/14388)

68eb27a

am17an commited on Jun 30

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158)

add5c0f

Sigbjørn Skjæret

ggerganov

OccamRazor Akarshan

jeffbolznv commited on Jun 29

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366)

737f12d

jeffbolznv slaren commited on Jun 29

ggml : add ggml_set_rows (llama/14274)

ac46a22

rgerganov

ggerganov commited on Jun 27

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)

fea8f94

taronaeo slaren commited on Jun 25

ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)

88e7829

Acly commited on Jul 1

Add `ggml_roll` (ggml/1274)

71923e5

Acly commited on Jun 18

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995)

d5d55f2

Max Krasnyansky Diego Devesa commited on May 31

ggml : add ggml_repeat_4d (llama/13824)

3fe8af8

ngxson HF Staff commited on May 27

ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247)

3c9a1d2

rgerganov commited on May 30

ggml : fix the order of ggml_unary_op (llama/13718)

bdae2b3

ngxson HF Staff commited on May 23

ggml : add ggml_gelu_erf() (llama/13667)

6c9cd9a

ngxson HF Staff commited on May 21

mnist: fix segmentation fault (ggml/1227)

341f451

JohannesGaessler commited on May 19

llama/ggml: add LLM training support (llama/10544)

8d3b3c1

JohannesGaessler commited on May 12

Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386)

418769d

David Huang commited on May 11

CUDA: fix bad asserts for partial offload (llama/13337)

23e676b

JohannesGaessler commited on May 6

CUDA: fix logic for clearing padding with -ngl 0 (llama/13320)

c3e51a2

JohannesGaessler commited on May 5

CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama/13137)

e9c9d4b

JohannesGaessler commited on Apr 28

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (llama/13107)

c47823e

sxx-404 commited on Apr 26

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama/12943)

691c071

rgerganov commited on Apr 25

ggml : fix ggml_gallocr_ptr type (ggml/1205)

cf46d5c

Diego Devesa commited on Apr 30

rpc : add RPC_CMD_HELLO (llama/12955)

ff22836

rgerganov commited on Apr 18

ggml : Depthwise 2D convolution (ggml/1152)

0c950d5

Acly commited on Apr 17

ggml : add bilinear upscale support (ggml/1185)

4c5e449

Diego Devesa commited on Apr 9

ggml : add more generic custom op, remove deprecated custom ops (ggml/1183)

ba7a5f8

Diego Devesa commited on Apr 9

metal : improve FA + improve MoE (llama/12612)

04a3389

ggerganov commited on Mar 28

rpc : send hash when tensor data is above some fixed threshold (llama/12496)

c39f9c4

rgerganov commited on Mar 28

llama: Add support for RWKV v7 architecture (llama/12412)

727de7e

mollysama commited on Mar 17

ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)

05466a9

Rémy O commited on Mar 6

ggml : portability fixes for VS 2017 (llama/12150)

49e3343

mgroeber9110 Marcus Groeber commited on Mar 4

ggml : upgrade init_tensor API to return a ggml_status (llama/11854)

d6b6852

William Tambellini slaren commited on Feb 28

ggml-cpu: Support s390x SIMD Instruction Set (llama/12019)

4aa54ec

Aaron Teo Jinyang He junchao-zhao commited on Feb 22

ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390)

9de6d81

Charles Xu commited on Feb 20

repo : update links to new url (llama/11886)

9705bb5

ggerganov commited on Feb 15

cleanup: fix compile warnings associated with gnu_printf (llama/11811)

ef6a968

bandoti commited on Feb 12

Commit History

ggml: initial IBM zDNN backend (llama/14975) 449e1a4

finetune: SGD optimizer, more CLI args (llama/13873) f585fe7

ggml : update `ggml_rope_multi` (llama/12665) b4896dc

llama : add gpt-oss (llama/15091) bf225d6

ggml : remove old kompute, cann (skip) (#3349) d321914 unverified

ggml: Add initial WebGPU backend (llama/14521) 0dd208f

sync : resolve conflicts (ggml/0) 497add0

ggml : add ggml_scale_bias (llama/14417) 573d50a

CUDA: add bilinear interpolation for upscale (llama/14563) 68ded09

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) f798922

ggml : fix FA mask dim 2 and 3 (llama/14505) a89dc81

llama : initial Mamba-2 support (llama/9126) 1b4087e

ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (llama/14435) ebacb3e

ggml : Callback before abort (llama/14481) ccee17d

ggml : add version function to get lib version (ggml/1286) 880f633

Add Conv2d for CPU (llama/14388) 68eb27a

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) add5c0f

vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 737f12d

ggml : add ggml_set_rows (llama/14274) ac46a22

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) fea8f94

ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285) 88e7829

Add `ggml_roll` (ggml/1274) 71923e5

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling (llama/12995) d5d55f2

ggml : add ggml_repeat_4d (llama/13824) 3fe8af8

ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247) 3c9a1d2

ggml : fix the order of ggml_unary_op (llama/13718) bdae2b3

ggml : add ggml_gelu_erf() (llama/13667) 6c9cd9a

mnist: fix segmentation fault (ggml/1227) 341f451

llama/ggml: add LLM training support (llama/10544) 8d3b3c1

Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (llama/13386) 418769d

CUDA: fix bad asserts for partial offload (llama/13337) 23e676b

CUDA: fix logic for clearing padding with -ngl 0 (llama/13320) c3e51a2

CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (llama/13137) e9c9d4b

ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (llama/13107) c47823e

rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (llama/12943) 691c071

ggml : fix ggml_gallocr_ptr type (ggml/1205) cf46d5c

rpc : add RPC_CMD_HELLO (llama/12955) ff22836

ggml : Depthwise 2D convolution (ggml/1152) 0c950d5

ggml : add bilinear upscale support (ggml/1185) 4c5e449

ggml : add more generic custom op, remove deprecated custom ops (ggml/1183) ba7a5f8

metal : improve FA + improve MoE (llama/12612) 04a3389

rpc : send hash when tensor data is above some fixed threshold (llama/12496) c39f9c4

llama: Add support for RWKV v7 architecture (llama/12412) 727de7e

ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154) 05466a9

ggml : portability fixes for VS 2017 (llama/12150) 49e3343

ggml : upgrade init_tensor API to return a ggml_status (llama/11854) d6b6852

ggml-cpu: Support s390x SIMD Instruction Set (llama/12019) 4aa54ec

ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390) 9de6d81

repo : update links to new url (llama/11886) 9705bb5

cleanup: fix compile warnings associated with gnu_printf (llama/11811) ef6a968