@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
attention
core
cutlass_extensions
gdn
kimi_k3
mamba
moe
quantization
activation_kernels.cu
async_util.cuh
cache_kernels.cu
cache_kernels_fused.cu
concat_mla_q.cuh
cooperative_topk.cu
cooperative_topk.cuh
cub_helpers.h
cuda_utils_kernels.cu
cuda_vec_utils.cuh
cuda_view.cu
custom_all_gather_reduce_scatter.cu
custom_all_gather_reduce_scatter_ops.cpp
custom_all_reduce.cu
dispatch_utils.h
dsv3_fused_a_gemm.cu
fp32_router_gemm.cu
fp32_router_gemm_entry.cu
fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu
fused_kimi_k3_mla_key_concat_kv_cache_kernel.cu
fused_minimax_m3_qknorm_rope_kv_insert_kernel.cu
fused_qknorm_rope_kernel.cu
hisparse_kernels.cu
launch_bounds_utils.h
layernorm_kernels.cu
layernorm_quant_kernels.cu
minimax_reduce_rms_kernel.cu
minimax_reduce_rms_kernel.h
ngram_embedding_kernels.cu
nvfp4_ds_mla_cache.h
nvfp4_ds_mla_cache_kernels.cu
nvfp4_kv_cache_kernels.cu
ops.h
persistent_topk.cuh
pos_encoding_kernels.cu
sampled_topk.cuh
sampler.cu
topk.cu
topk_histogram_4096.cuh
torch_bindings.cpp
torch_utils.h
type_convert.cuh
vocab_parallel_embedding_kernels.cu