ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-29 16:58:51 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
44bc2767fd
whisper.cpp/scripts/bench-all-gg.txt
Georgi Gerganov 7094ea5e75
whisper : use flash attention (#2152) 
* whisper : use flash attention in the encoder

* whisper : add kv_pad

* whisper : remove extra backend instance (huh?)

* whisper : use FA for cross-attention

* whisper : use FA for self-attention

* whisper : simplify encoder FA

* whisper : add flash_attn runtime parameter

* scripts : add bench log

* scripts : add M1 Pro bench log
2024-05-15 09:38:19 +03:00

299 lines
20 KiB
Plaintext
Raw Blame History

## M1 Pro
make -j && ./scripts/bench-all.sh 8
Running memcpy benchmark
memcpy: 39.10 GB/s (heat-up)
memcpy: 44.75 GB/s ( 1 thread)
memcpy: 44.78 GB/s ( 1 thread)
memcpy: 44.97 GB/s ( 2 thread)
memcpy: 48.04 GB/s ( 3 thread)
memcpy: 50.55 GB/s ( 4 thread)
memcpy: 55.20 GB/s ( 5 thread)
memcpy: 65.60 GB/s ( 6 thread)
memcpy: 70.64 GB/s ( 7 thread)
memcpy: 73.34 GB/s ( 8 thread)
sum: -5120002535.000000
make -j && ./scripts/bench-all.sh 1 0 0
Running ggml_mul_mat benchmark with 1 threads
64 x 64: Q4_0 237.1 GFLOPS (128 runs) | Q4_1 168.6 GFLOPS (128 runs)
64 x 64: Q5_0 136.4 GFLOPS (128 runs) | Q5_1 135.6 GFLOPS (128 runs) | Q8_0 243.1 GFLOPS (128 runs)
64 x 64: F16 140.4 GFLOPS (128 runs) | F32 316.6 GFLOPS (128 runs)
128 x 128: Q4_0 496.6 GFLOPS (128 runs) | Q4_1 348.6 GFLOPS (128 runs)
128 x 128: Q5_0 273.2 GFLOPS (128 runs) | Q5_1 274.1 GFLOPS (128 runs) | Q8_0 505.1 GFLOPS (128 runs)
128 x 128: F16 300.4 GFLOPS (128 runs) | F32 653.9 GFLOPS (128 runs)
256 x 256: Q4_0 791.7 GFLOPS (128 runs) | Q4_1 615.3 GFLOPS (128 runs)
256 x 256: Q5_0 651.0 GFLOPS (128 runs) | Q5_1 674.7 GFLOPS (128 runs) | Q8_0 803.1 GFLOPS (128 runs)
256 x 256: F16 869.6 GFLOPS (128 runs) | F32 957.2 GFLOPS (128 runs)
512 x 512: Q4_0 973.3 GFLOPS (128 runs) | Q4_1 897.9 GFLOPS (128 runs)
512 x 512: Q5_0 1078.8 GFLOPS (128 runs) | Q5_1 998.4 GFLOPS (128 runs) | Q8_0 752.4 GFLOPS (128 runs)
512 x 512: F16 892.5 GFLOPS (128 runs) | F32 1399.6 GFLOPS (128 runs)
1024 x 1024: Q4_0 1402.7 GFLOPS (128 runs) | Q4_1 1218.5 GFLOPS (128 runs)
1024 x 1024: Q5_0 1444.8 GFLOPS (128 runs) | Q5_1 1444.7 GFLOPS (128 runs) | Q8_0 1395.7 GFLOPS (128 runs)
1024 x 1024: F16 1524.1 GFLOPS (128 runs) | F32 1726.6 GFLOPS (128 runs)
2048 x 2048: Q4_0 1479.4 GFLOPS ( 87 runs) | Q4_1 1378.5 GFLOPS ( 81 runs)
2048 x 2048: Q5_0 1454.6 GFLOPS ( 85 runs) | Q5_1 1462.9 GFLOPS ( 86 runs) | Q8_0 1483.2 GFLOPS ( 87 runs)
2048 x 2048: F16 1488.0 GFLOPS ( 87 runs) | F32 1538.2 GFLOPS ( 90 runs)
4096 x 4096: Q4_0 1509.7 GFLOPS ( 11 runs) | Q4_1 1433.0 GFLOPS ( 11 runs)
4096 x 4096: Q5_0 1422.4 GFLOPS ( 11 runs) | Q5_1 1437.0 GFLOPS ( 11 runs) | Q8_0 1523.0 GFLOPS ( 12 runs)
4096 x 4096: F16 1551.3 GFLOPS ( 12 runs) | F32 1451.0 GFLOPS ( 11 runs)
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| M1 Pro | METAL | tiny | 1 | 0 | 39.21 | 1.74 | 0.61 | 0.04 | 22c96b4 |
| M1 Pro | METAL | base | 1 | 0 | 70.76 | 2.60 | 0.93 | 0.06 | 22c96b4 |
| M1 Pro | METAL | small | 1 | 0 | 217.28 | 6.42 | 2.14 | 0.17 | 22c96b4 |
| M1 Pro | METAL | medium | 1 | 0 | 596.74 | 14.43 | 4.75 | 0.45 | 22c96b4 |
make -j && ./scripts/bench-all.sh 1 1 1
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| M1 Pro | METAL | tiny | 1 | 1 | 30.77 | 1.59 | 0.54 | 0.03 | 22c96b4 |
| M1 Pro | METAL | base | 1 | 1 | 60.42 | 2.29 | 0.81 | 0.05 | 22c96b4 |
| M1 Pro | METAL | small | 1 | 1 | 183.82 | 5.12 | 1.81 | 0.14 | 22c96b4 |
| M1 Pro | METAL | medium | 1 | 1 | 517.92 | 11.60 | 4.01 | 0.38 | 22c96b4 |
## M2 Ultra
make -j && ./scripts/bench-all.sh 8
Running memcpy benchmark
memcpy: 46.58 GB/s (heat-up)
memcpy: 54.16 GB/s ( 1 thread)
memcpy: 54.23 GB/s ( 1 thread)
memcpy: 99.63 GB/s ( 2 thread)
memcpy: 140.59 GB/s ( 3 thread)
memcpy: 176.52 GB/s ( 4 thread)
memcpy: 158.90 GB/s ( 5 thread)
memcpy: 163.00 GB/s ( 6 thread)
memcpy: 189.69 GB/s ( 7 thread)
memcpy: 197.15 GB/s ( 8 thread)
sum: -5120002007.000000
make -j && ./scripts/bench-all.sh 1
Running ggml_mul_mat benchmark with 1 threads
64 x 64: Q4_0 245.8 GFLOPS (128 runs) | Q4_1 168.6 GFLOPS (128 runs)
64 x 64: Q5_0 115.7 GFLOPS (128 runs) | Q5_1 125.9 GFLOPS (128 runs) | Q8_0 215.8 GFLOPS (128 runs)
64 x 64: F16 139.5 GFLOPS (128 runs) | F32 337.2 GFLOPS (128 runs)
128 x 128: Q4_0 494.8 GFLOPS (128 runs) | Q4_1 350.4 GFLOPS (128 runs)
128 x 128: Q5_0 257.1 GFLOPS (128 runs) | Q5_1 261.4 GFLOPS (128 runs) | Q8_0 509.4 GFLOPS (128 runs)
128 x 128: F16 302.3 GFLOPS (128 runs) | F32 672.8 GFLOPS (128 runs)
256 x 256: Q4_0 795.7 GFLOPS (128 runs) | Q4_1 663.7 GFLOPS (128 runs)
256 x 256: Q5_0 737.8 GFLOPS (128 runs) | Q5_1 757.6 GFLOPS (128 runs) | Q8_0 827.7 GFLOPS (128 runs)
256 x 256: F16 872.6 GFLOPS (128 runs) | F32 956.3 GFLOPS (128 runs)
512 x 512: Q4_0 1188.0 GFLOPS (128 runs) | Q4_1 1085.0 GFLOPS (128 runs)
512 x 512: Q5_0 1421.1 GFLOPS (128 runs) | Q5_1 1454.9 GFLOPS (128 runs) | Q8_0 1191.4 GFLOPS (128 runs)
512 x 512: F16 1577.4 GFLOPS (128 runs) | F32 1982.0 GFLOPS (128 runs)
1024 x 1024: Q4_0 2342.6 GFLOPS (128 runs) | Q4_1 1955.8 GFLOPS (128 runs)
1024 x 1024: Q5_0 2306.7 GFLOPS (128 runs) | Q5_1 2217.0 GFLOPS (128 runs) | Q8_0 2230.7 GFLOPS (128 runs)
1024 x 1024: F16 2593.8 GFLOPS (128 runs) | F32 3269.0 GFLOPS (128 runs)
2048 x 2048: Q4_0 3735.7 GFLOPS (128 runs) | Q4_1 3205.3 GFLOPS (128 runs)
2048 x 2048: Q5_0 3584.5 GFLOPS (128 runs) | Q5_1 3621.7 GFLOPS (128 runs) | Q8_0 3622.3 GFLOPS (128 runs)
2048 x 2048: F16 3763.6 GFLOPS (128 runs) | F32 4153.3 GFLOPS (128 runs)
4096 x 4096: Q4_0 3891.1 GFLOPS ( 29 runs) | Q4_1 3554.0 GFLOPS ( 26 runs)
4096 x 4096: Q5_0 3753.1 GFLOPS ( 28 runs) | Q5_1 3750.1 GFLOPS ( 28 runs) | Q8_0 3768.5 GFLOPS ( 28 runs)
4096 x 4096: F16 3864.2 GFLOPS ( 29 runs) | F32 3970.5 GFLOPS ( 29 runs)
make -j && ./scripts/bench-all.sh 1 1 0
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| M2 ULTRA | METAL | tiny | 1 | 0 | 12.32 | 1.35 | 0.49 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 0 | 11.65 | 1.30 | 0.51 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 0 | 12.08 | 1.30 | 0.51 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | base | 1 | 0 | 17.58 | 1.90 | 0.76 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | base-q5_0 | 1 | 0 | 18.89 | 1.86 | 0.79 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | base-q5_1 | 1 | 0 | 20.69 | 1.88 | 0.79 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | small | 1 | 0 | 49.32 | 3.85 | 1.71 | 0.05 | 22c96b4 |
| M2 ULTRA | METAL | small-q5_0 | 1 | 0 | 54.91 | 3.81 | 1.82 | 0.06 | 22c96b4 |
| M2 ULTRA | METAL | small-q5_1 | 1 | 0 | 54.92 | 3.81 | 1.79 | 0.06 | 22c96b4 |
| M2 ULTRA | METAL | medium | 1 | 0 | 134.34 | 8.04 | 3.82 | 0.13 | 22c96b4 |
| M2 ULTRA | METAL | medium-q5_0 | 1 | 0 | 151.68 | 7.59 | 4.07 | 0.14 | 22c96b4 |
| M2 ULTRA | METAL | medium-q5_1 | 1 | 0 | 151.58 | 7.67 | 4.07 | 0.14 | 22c96b4 |
| M2 ULTRA | METAL | medium-dis | 1 | 0 | 120.82 | 1.07 | 0.41 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | large-v2 | 1 | 0 | 235.63 | 12.27 | 5.85 | 0.22 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 0 | 273.38 | 11.17 | 6.40 | 0.26 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 0 | 272.44 | 11.32 | 6.29 | 0.26 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-dis | 1 | 0 | 212.51 | 1.20 | 0.47 | 0.02 | 22c96b4 |
make -j && ./scripts/bench-all.sh 1 1 1
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| M2 ULTRA | METAL | tiny | 1 | 1 | 9.07 | 1.33 | 0.45 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | tiny-q5_0 | 1 | 1 | 9.74 | 1.33 | 0.47 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | tiny-q5_1 | 1 | 1 | 8.93 | 1.31 | 0.46 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | base | 1 | 1 | 15.75 | 1.87 | 0.71 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | base-q5_0 | 1 | 1 | 17.04 | 1.83 | 0.74 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | base-q5_1 | 1 | 1 | 17.17 | 1.83 | 0.74 | 0.02 | 22c96b4 |
| M2 ULTRA | METAL | small | 1 | 1 | 42.33 | 3.64 | 1.60 | 0.05 | 22c96b4 |
| M2 ULTRA | METAL | small-q5_0 | 1 | 1 | 47.61 | 3.63 | 1.70 | 0.05 | 22c96b4 |
| M2 ULTRA | METAL | small-q5_1 | 1 | 1 | 47.70 | 3.66 | 1.68 | 0.05 | 22c96b4 |
| M2 ULTRA | METAL | medium | 1 | 1 | 114.42 | 7.53 | 3.55 | 0.11 | 22c96b4 |
| M2 ULTRA | METAL | medium-q5_0 | 1 | 1 | 132.63 | 7.02 | 3.77 | 0.13 | 22c96b4 |
| M2 ULTRA | METAL | medium-q5_1 | 1 | 1 | 132.28 | 7.10 | 3.76 | 0.13 | 22c96b4 |
| M2 ULTRA | METAL | medium-dis | 1 | 1 | 102.34 | 1.01 | 0.42 | 0.01 | 22c96b4 |
| M2 ULTRA | METAL | large-v2 | 1 | 1 | 203.01 | 11.03 | 5.45 | 0.20 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-q5_0 | 1 | 1 | 240.05 | 10.18 | 5.98 | 0.23 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-q5_1 | 1 | 1 | 239.22 | 10.23 | 5.87 | 0.23 | 22c96b4 |
| M2 ULTRA | METAL | large-v2-dis | 1 | 1 | 181.14 | 1.14 | 0.48 | 0.02 | 22c96b4 |
## Ryzen 9 5950X + RTX 2060
make -j && ./scripts/bench-all.sh 8 0 0
Running memcpy benchmark
memcpy: 12.36 GB/s (heat-up)
memcpy: 12.33 GB/s ( 1 thread)
memcpy: 12.38 GB/s ( 1 thread)
memcpy: 14.48 GB/s ( 2 thread)
memcpy: 15.00 GB/s ( 3 thread)
memcpy: 14.77 GB/s ( 4 thread)
memcpy: 14.60 GB/s ( 5 thread)
memcpy: 14.57 GB/s ( 6 thread)
memcpy: 14.34 GB/s ( 7 thread)
memcpy: 14.40 GB/s ( 8 thread)
sum: -5119998076.000000
Running ggml_mul_mat benchmark with 8 threads
64 x 64: Q4_0 3.1 GFLOPS (128 runs) | Q4_1 3.1 GFLOPS (128 runs)
64 x 64: Q5_0 3.0 GFLOPS (128 runs) | Q5_1 2.9 GFLOPS (128 runs) | Q8_0 3.1 GFLOPS (128 runs)
64 x 64: F16 3.0 GFLOPS (128 runs) | F32 3.0 GFLOPS (128 runs)
128 x 128: Q4_0 21.1 GFLOPS (128 runs) | Q4_1 20.3 GFLOPS (128 runs)
128 x 128: Q5_0 20.6 GFLOPS (128 runs) | Q5_1 20.4 GFLOPS (128 runs) | Q8_0 22.1 GFLOPS (128 runs)
128 x 128: F16 21.7 GFLOPS (128 runs) | F32 21.7 GFLOPS (128 runs)
256 x 256: Q4_0 105.7 GFLOPS (128 runs) | Q4_1 94.4 GFLOPS (128 runs)
256 x 256: Q5_0 94.8 GFLOPS (128 runs) | Q5_1 87.5 GFLOPS (128 runs) | Q8_0 107.2 GFLOPS (128 runs)
256 x 256: F16 95.1 GFLOPS (128 runs) | F32 94.3 GFLOPS (128 runs)
512 x 512: Q4_0 214.7 GFLOPS (128 runs) | Q4_1 189.8 GFLOPS (128 runs)
512 x 512: Q5_0 187.7 GFLOPS (128 runs) | Q5_1 176.2 GFLOPS (128 runs) | Q8_0 252.2 GFLOPS (128 runs)
512 x 512: F16 220.8 GFLOPS (128 runs) | F32 218.3 GFLOPS (128 runs)
1024 x 1024: Q4_0 333.7 GFLOPS (128 runs) | Q4_1 305.8 GFLOPS (128 runs)
1024 x 1024: Q5_0 283.2 GFLOPS (128 runs) | Q5_1 268.2 GFLOPS (125 runs) | Q8_0 394.1 GFLOPS (128 runs)
1024 x 1024: F16 355.0 GFLOPS (128 runs) | F32 313.0 GFLOPS (128 runs)
2048 x 2048: Q4_0 395.0 GFLOPS ( 23 runs) | Q4_1 380.6 GFLOPS ( 23 runs)
2048 x 2048: Q5_0 336.6 GFLOPS ( 20 runs) | Q5_1 318.4 GFLOPS ( 19 runs) | Q8_0 482.6 GFLOPS ( 29 runs)
2048 x 2048: F16 424.5 GFLOPS ( 25 runs) | F32 337.7 GFLOPS ( 20 runs)
4096 x 4096: Q4_0 412.8 GFLOPS ( 4 runs) | Q4_1 405.1 GFLOPS ( 3 runs)
4096 x 4096: Q5_0 346.0 GFLOPS ( 3 runs) | Q5_1 334.6 GFLOPS ( 3 runs) | Q8_0 502.6 GFLOPS ( 4 runs)
4096 x 4096: F16 412.5 GFLOPS ( 4 runs) | F32 274.0 GFLOPS ( 3 runs)
| CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Ryzen 9 5950X | AVX2 | tiny | 8 | 0 | 195.29 | 1.57 | 0.51 | 0.26 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | tiny-q5_0 | 8 | 0 | 213.33 | 1.10 | 0.50 | 0.30 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | tiny-q5_1 | 8 | 0 | 219.38 | 1.18 | 0.53 | 0.32 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | base | 8 | 0 | 424.85 | 3.71 | 1.03 | 0.46 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | base-q5_0 | 8 | 0 | 473.61 | 1.81 | 0.82 | 0.52 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | base-q5_1 | 8 | 0 | 484.14 | 1.92 | 0.85 | 0.56 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | small | 8 | 0 | 1458.32 | 12.66 | 3.09 | 1.26 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | small-q5_0 | 8 | 0 | 1673.22 | 6.42 | 2.18 | 1.45 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | small-q5_1 | 8 | 0 | 1724.78 | 6.72 | 2.32 | 1.52 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | medium | 8 | 0 | 4333.87 | 36.80 | 8.56 | 3.37 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | medium-q5_0 | 8 | 0 | 5194.09 | 19.21 | 5.71 | 3.97 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | medium-q5_1 | 8 | 0 | 5450.39 | 20.01 | 5.99 | 4.17 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | medium-dis | 8 | 0 | 3995.19 | 5.08 | 1.21 | 0.55 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | large-v2 | 8 | 0 | 8056.16 | 69.74 | 16.11 | 6.13 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | large-v2-q5_0 | 8 | 0 | 9799.58 | 35.16 | 10.49 | 7.28 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | large-v2-q5_1 | 8 | 0 | ms | 36.74 | 11.02 | 7.65 | 22c96b4 |
| Ryzen 9 5950X | AVX2 | large-v2-dis | 8 | 0 | 7490.03 | 7.40 | 1.70 | 0.72 | 22c96b4 |
WHISPER_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 0
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| RTX 2060 | AVX2 CUDA | tiny | 8 | 0 | 12.54 | 0.93 | 0.29 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | tiny-q5_0 | 8 | 0 | 12.73 | 0.98 | 0.24 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | tiny-q5_1 | 8 | 0 | 12.72 | 0.99 | 0.24 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base | 8 | 0 | 24.14 | 1.28 | 0.41 | 0.03 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base-q5_0 | 8 | 0 | 24.58 | 1.38 | 0.35 | 0.03 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base-q5_1 | 8 | 0 | 24.58 | 1.37 | 0.35 | 0.03 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small | 8 | 0 | 74.70 | 2.91 | 0.84 | 0.07 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small-q5_0 | 8 | 0 | 76.12 | 2.84 | 0.77 | 0.08 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small-q5_1 | 8 | 0 | 76.14 | 2.84 | 0.76 | 0.08 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium | 8 | 0 | 200.69 | 6.46 | 1.83 | 0.17 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-q5_0 | 8 | 0 | 204.80 | 5.90 | 1.65 | 0.19 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-q5_1 | 8 | 0 | 205.61 | 5.85 | 1.61 | 0.19 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-dis | 8 | 0 | 186.17 | 0.86 | 0.24 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2 | 8 | 0 | 347.22 | 10.36 | 2.82 | 0.29 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-q5_0 | 8 | 0 | 357.06 | 8.81 | 2.58 | 0.34 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-q5_1 | 8 | 0 | 356.97 | 8.62 | 2.49 | 0.33 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-dis | 8 | 0 | 318.05 | 1.03 | 0.34 | 0.04 | 22c96b4 |
WHISPER_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 1
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| RTX 2060 | AVX2 CUDA | tiny | 8 | 1 | 7.21 | 0.76 | 0.29 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | tiny-q5_0 | 8 | 1 | 7.42 | 0.82 | 0.18 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | tiny-q5_1 | 8 | 1 | 7.38 | 0.82 | 0.18 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base | 8 | 1 | 13.49 | 1.04 | 0.36 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base-q5_0 | 8 | 1 | 13.94 | 1.13 | 0.26 | 0.03 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | base-q5_1 | 8 | 1 | 13.94 | 1.14 | 0.26 | 0.03 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small | 8 | 1 | 42.81 | 2.33 | 0.69 | 0.05 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small-q5_0 | 8 | 1 | 44.43 | 2.25 | 0.59 | 0.06 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | small-q5_1 | 8 | 1 | 44.11 | 2.24 | 0.58 | 0.06 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium | 8 | 1 | 115.47 | 5.17 | 1.45 | 0.11 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-q5_0 | 8 | 1 | 120.37 | 4.63 | 1.25 | 0.13 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-q5_1 | 8 | 1 | 120.28 | 4.55 | 1.21 | 0.13 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | medium-dis | 8 | 1 | 101.69 | 0.75 | 0.20 | 0.02 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2 | 8 | 1 | 205.67 | 8.49 | 2.19 | 0.18 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-q5_0 | 8 | 1 | 214.07 | 6.88 | 1.94 | 0.22 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-q5_1 | 8 | 1 | 213.98 | 6.70 | 1.86 | 0.22 | 22c96b4 |
| RTX 2060 | AVX2 CUDA | large-v2-dis | 8 | 1 | 176.71 | 0.91 | 0.31 | 0.03 | 22c96b4 |
# V100
WHISPER_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 0
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| V100 | AVX2 CUDA | tiny | 1 | 0 | 6.21 | 1.11 | 0.30 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | tiny-q5_1 | 1 | 0 | 5.97 | 1.10 | 0.26 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | base | 1 | 0 | 10.95 | 1.47 | 0.42 | 0.03 | 22c96b4 |
| V100 | AVX2 CUDA | base-q5_1 | 1 | 0 | 11.13 | 1.53 | 0.36 | 0.03 | 22c96b4 |
| V100 | AVX2 CUDA | small | 1 | 0 | 31.57 | 2.96 | 0.84 | 0.05 | 22c96b4 |
| V100 | AVX2 CUDA | small-q5_1 | 1 | 0 | 32.19 | 3.14 | 0.75 | 0.05 | 22c96b4 |
| V100 | AVX2 CUDA | medium | 1 | 0 | 85.88 | 6.49 | 1.80 | 0.10 | 22c96b4 |
| V100 | AVX2 CUDA | medium-q5_0 | 1 | 0 | 87.53 | 5.82 | 1.37 | 0.10 | 22c96b4 |
| V100 | AVX2 CUDA | large-v2 | 1 | 0 | 142.23 | 8.92 | 2.62 | 0.15 | 22c96b4 |
WHISPER_CUDA=1 make -j && ./scripts/bench-all.sh 8 1 1
| GPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| V100 | AVX2 CUDA | tiny | 1 | 1 | 3.96 | 0.82 | 0.24 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | tiny-q5_1 | 1 | 1 | 4.05 | 0.85 | 0.18 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | base | 1 | 1 | 7.21 | 1.16 | 0.36 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | base-q5_1 | 1 | 1 | 7.39 | 1.21 | 0.26 | 0.02 | 22c96b4 |
| V100 | AVX2 CUDA | small | 1 | 1 | 19.81 | 2.41 | 0.71 | 0.04 | 22c96b4 |
| V100 | AVX2 CUDA | small-q5_1 | 1 | 1 | 20.50 | 2.31 | 0.51 | 0.04 | 22c96b4 |
| V100 | AVX2 CUDA | medium | 1 | 1 | 56.02 | 4.89 | 1.44 | 0.07 | 22c96b4 |
| V100 | AVX2 CUDA | medium-q5_0 | 1 | 1 | 57.85 | 4.73 | 1.09 | 0.08 | 22c96b4 |
| V100 | AVX2 CUDA | large-v2 | 1 | 1 | 92.73 | 7.18 | 2.14 | 0.10 | 22c96b4 |
Reference in New Issue View Git Blame Copy Permalink