baseten/whisper-large-v3-TRT-L4-bs4
Updated
baseten/vicuna-medusa_i1024_o1024_bs_fp16_tp1-tllm_0.9.0.dev2024040200
baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs32_fp8_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/NousResearch-Nous-Hermes-2-SOLAR-10.7B_i6000_o1024_bs128_fp8_tp1-tllm_0.9.0.dev2024022000
Updated
baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp8_tp2-tllm_0.9.0.dev2024022000-VS
Updated
baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp8_tp1-tllm_0.9.0.dev2024022000-VS
Updated
baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp16_tp1-tllm_0.9.0.dev2024022000-VS
Updated
baseten/solar-SOLAR-10.7B-v1.0_i2000_o512_bs12_fp16_tp2-tllm_0.9.0.dev2024022000-VS
Updated
baseten/pg-ngc-solar-test
Updated
baseten/solar_i6000_o1024_bs64_fp8_tp1-tllm_0.9.0.dev2024022000-gemm-disabled
Updated
baseten/solar_i6000_o1024_bs96_fp8_tp1-tllm_0.9.0.dev2024022000
Updated
baseten/solar_i6000_o1024_bs64_fp8_tp1-tllm_0.9.0.dev2024022000
Updated
baseten/solar_i6000_o1024_bs64_fp8_tp1-tllm_0.9.0.dev2024032600
Updated
baseten/solar_fp8_tp2_weights
Updated
baseten/solar_fp8_tp1_weights
Updated
baseten/solar_fp8_tp1_i6000_o1000_bs64-tllm_0.9.0.dev2024022000
Updated
baseten/solar_fp8_tp2_i6000_o1000_bs128-tllm_0.9.0.dev2024022000
Updated
baseten/solar_fp8_tp1_i6000_o1000_bs84-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs96_tp8-tllm_0.9.0.dev2024032600
Updated
baseten/llama-7b_fp8_tp2_i1024_o1024_bs64-tllm_0.9.0.dev2024022000
Updated
baseten/llama-7b_fp8_tp2_i100_o400_bs24-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs96_tp8-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs48_tp8-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs16_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs32_int8_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs96_int8_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs364_tp8-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs128_int8_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i6000_o1024_bs64_fp16_tp2-tllm_0.9.0.dev2024022000
Updated
baseten/dolphin_i8192_o1024_bs12_fp16_tp2-tllm_0.9.0.dev2024022000
Updated