whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src /ggml-cpu /ggml-cpu-quants.c

Commit History

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0)

f695cbf

ggerganov commited on Mar 27

ggml : add SVE support for q6_K_q8_K (llama/12361)

607a196

fj-y-saito commited on Mar 18

ggml-cpu: faster AVX2 variant for IQ1_M (llama/12216)

591cbfb

Rémy O commited on Mar 7

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: aarch64: implement SVE kernels for q2_k_q8_k vector dot (llama/12064)

459beb1

Prashant Vithule vithulep commited on Feb 28

ggml-cpu: Fix build with sve (llama/12059)

4be146e

mollysama commited on Feb 25

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

4aa54ec

Aaron Teo Jinyang He junchao-zhao commited on Feb 22

ggml: aarch64: implement SVE kernels for q3_K_q8_K vector dot (llama/11917)

1a1acd2

Prashant Vithule vithulep

ggerganov commited on Feb 20

ggml: optimize some vec dot functions for LoongArch ASX (llama/11842)

e3acbfc

Jinyang He commited on Feb 14

ggml : x2 speed for WASM by optimizing SIMD (llama/11453)

464a186

Xuan-Son Nguyen camel-cdr commited on Feb 12

ggml : optimize and build warning fix for LoongArch (llama/11709)

b82d241

Jinyang He commited on Feb 7

ggml : fix LoongArch compile error with 128-bit SIMD (llama/11701)

f7296aa

junchao-zhao commited on Feb 6

ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (llama/11227)

bf3dc93

fj-y-saito

ggerganov commited on Jan 16

ggml : fixes for AVXVNNI instruction set with MSVC and Clang (llama/11027)

d13ac16

Srihari-mcw slaren commited on Dec 31, 2024

ggml : fix I8MM Q4_1 scaling factor conversion (llama/10562)

664be9a

ggerganov commited on Nov 29, 2024

ggml : fix row condition for i8mm kernels (llama/10561)

01c713f

ggerganov commited on Nov 28, 2024

AVX BF16 and single scale quant optimizations (llama/10212)

e6ffed3

Eve commited on Nov 15, 2024

ggml : build backends as libraries (llama/10256)

3dc93f3

Diego Devesa

ggerganov R0CKSTAR commited on Nov 14, 2024

Commit History

ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0) f695cbf

ggml : add SVE support for q6_K_q8_K (llama/12361) 607a196

ggml-cpu: faster AVX2 variant for IQ1_M (llama/12216) 591cbfb

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: aarch64: implement SVE kernels for q2_k_q8_k vector dot (llama/12064) 459beb1

ggml-cpu: Fix build with sve (llama/12059) 4be146e

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

ggml: aarch64: implement SVE kernels for q3_K_q8_K vector dot (llama/11917) 1a1acd2

ggml: optimize some vec dot functions for LoongArch ASX (llama/11842) e3acbfc

ggml : x2 speed for WASM by optimizing SIMD (llama/11453) 464a186

ggml : optimize and build warning fix for LoongArch (llama/11709) b82d241

ggml : fix LoongArch compile error with 128-bit SIMD (llama/11701) f7296aa

ggml: aarch64: implement SVE kernels for q4_K_q8_K vector dot (llama/11227) bf3dc93

ggml : fixes for AVXVNNI instruction set with MSVC and Clang (llama/11027) d13ac16

ggml : fix I8MM Q4_1 scaling factor conversion (llama/10562) 664be9a

ggml : fix row condition for i8mm kernels (llama/10561) 01c713f

AVX BF16 and single scale quant optimizations (llama/10212) e6ffed3

ggml : build backends as libraries (llama/10256) 3dc93f3