Instructions to use replicate/flashinfer-draft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/flashinfer-draft with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("replicate/flashinfer-draft") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
- batch_decode_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False
- batch_mla_attention_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_ckv_512_head_dim_kpe_64_profiler_False
- batch_mla_attention_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_ckv_512_head_dim_kpe_64_profiler_False_sm90
- batch_mla_attention_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_ckv_512_head_dim_kpe_64_profiler_False
- batch_mla_attention_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_ckv_512_head_dim_kpe_64_profiler_False_sm90
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_192_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_bf16_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_e4m3_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_e4m3_dtype_kv_e4m3_dtype_o_bf16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_e4m3_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_e4m3_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_e4m3_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_192_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True_f16qk_False_sm90
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False_f16qk_False
- batch_prefill_with_kv_cache_dtype_q_f16_dtype_kv_f16_dtype_o_f16_dtype_idx_i32_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False_f16qk_False
- single_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_head_dim_qk_128_head_dim_vo_128_posenc_0_use_swa_False_use_logits_cap_False
- single_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_head_dim_qk_256_head_dim_vo_256_posenc_0_use_swa_True_use_logits_cap_True
- single_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_False_use_logits_cap_False
- single_decode_with_kv_cache_dtype_q_bf16_dtype_kv_bf16_dtype_o_bf16_head_dim_qk_64_head_dim_vo_64_posenc_0_use_swa_True_use_logits_cap_False