AI & ML interests
None defined yet.
Recent Activity
Remove update_gdn_workloads.py
#301 opened 1 day ago
by
averyyh
Add gqa_paged_decode_h24_kv8_d128_ps64: solution + workloads + blobs + def + tests
#251 opened 9 days ago
by
averyyh
Add gqa_paged_decode_h24_kv8_d128_ps64: solution + workloads + blobs + eval trace (Llama 3.2 3B)
1
#247 opened 9 days ago
by
averyyh
Add Llama 4 Scout 17B-16E complete workloads, solutions, and definitions
#262 opened 5 days ago
by
averyyh
Add workloads: gqa_paged_prefill_causal_h6_kv1_d128_ps1
#275 opened 4 days ago
by
averyyh
Add workloads: gqa_paged_prefill_causal_h6_kv1_d128_ps64
#276 opened 4 days ago
by
averyyh
Add workloads: trtllm_fp4_block_scale_routed_moe_topk1_e16_h5120_i8192
#271 opened 4 days ago
by
averyyh
Add workloads: gqa_paged_decode_h6_kv1_d128_ps64
#278 opened 4 days ago
by
averyyh
Add workloads: gqa_ragged_prefill_causal_h6_kv1_d128
#279 opened 4 days ago
by
averyyh
Add workloads: gemm_n8192_k3072
#280 opened 4 days ago
by
averyyh
Add workloads: gemm_n3072_k6144
#281 opened 4 days ago
by
averyyh
Add workloads: gemm_n256_k3072
#282 opened 4 days ago
by
averyyh
feat: add MiniMax M2 definitions and baseline solutions (17 kernels)
1
#260 opened 6 days ago
by
averyyh
Add workloads: rope_with_cos_sin_cache_neox_style_d128_rd64
#274 opened 4 days ago
by
averyyh
Add workloads: fused_add_rmsnorm_h3072
#273 opened 4 days ago
by
averyyh
Add workloads: rmsnorm_h3072
#272 opened 4 days ago
by
averyyh
Add workloads: gqa_paged_decode_h6_kv1_d128_ps1
#277 opened 4 days ago
by
averyyh
Add workloads: trtllm_fp8_block_scale_moe_topk8_e256_h3072_i1536
#283 opened 4 days ago
by
averyyh
Add workloads: top_k_sampling_from_probs_v200064
#284 opened 4 days ago
by
averyyh
Add workloads: top_k_top_p_sampling_from_probs_v200064
#285 opened 4 days ago
by
averyyh