messages listlengths 3 3 | task stringlengths 35 39 | source stringclasses 1
value | lang stringclasses 2
values | speedup float64 0.02 5.42 |
|---|---|---|---|---|
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/cuda_agent_ops_6k/01219.py | rft_r1 | Triton | 5.415498 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/cuda_agent_ops_6k/01219.py | rft_r1 | Triton | 4.967145 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/drkernel_rl/cuda_llm_617176.py | rft_r1 | Triton | 4.597948 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/drkernel_rl/cuda_llm_929891.py | rft_r1 | Triton | 3.472791 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/drkernel_rl/cuda_llm_929891.py | rft_r1 | Triton | 3.423805 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/drkernel_rl/cuda_llm_812302.py | rft_r1 | CUDA | 2.691519 |
[
{
"role": "system",
"content": "You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (Hopper, sm_90).\nAvailable: torch, triton, flashinfer, deepgemm, tilelang, cute dsl, cutlass; native CUDA via torch.utils.cpp_extension.load_inline. No network.\nCode must be CUDA-graph capturable. Think ef... | external/cuda_agent_ops_6k/01239.py | rft_r1 | CUDA | 2.220569 |
[{"role":"system","content":"You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (H(...TRUNCATED) | external/drkernel_rl/cuda_llm_342840.py | rft_r1 | Triton | 1.778672 |
[{"role":"system","content":"You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (H(...TRUNCATED) | external/drkernel_rl/cuda_llm_342840.py | rft_r1 | CUDA | 1.772704 |
[{"role":"system","content":"You are an expert GPU kernel engineer working on one NVIDIA H200 SXM (H(...TRUNCATED) | external/drkernel_rl/cuda_llm_251426.py | rft_r1 | CUDA | 1.474552 |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 16