@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
flydsl_kernels
turboquant_soa
__init__.py
chunked_prefill_paged_decode.py
common.py
cp_common.py
dcp.py
flashmla.py
flydsl_turboquant_decode.py
int4_per_token_head.py
merge_attn_states.py
metadata.py
paged_attn.py
pcp.py
prefix_prefill.py
rocm_aiter_mla_merge.py
rocm_aiter_mla_sparse.py
rocm_paged_mxfp4_indexer.py
triton_attention_helpers.py
triton_decode_attention.py
triton_merge_attn_states.py
triton_prefill_attention.py
triton_reshape_and_cache_flash.py
triton_turboquant_decode.py
triton_turboquant_store.py
triton_unified_attention.py
triton_unified_attention_diffkv.py
vit_attn_wrappers.py
xpu_mla_sparse.py