biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Attention] MLA with chunked prefill (#12639)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2025-02-21 18:30:12 -05:00
committed by GitHub
parent 900edbfa48
commit 288cc6c234
18 changed files with 1910 additions and 1275 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
csrc/torch_bindings.cpp
View File

@@ -493,6 +493,12 @@ TORCH_LIBRARY_EXPAND(CONCAT(TORCH_EXTENSION_NAME, _cache_ops), cache_ops) {
"convert_fp8(Tensor! dst_cache, Tensor src_cache, float scale, "
"str kv_cache_dtype) -> ()");
cache_ops.impl("convert_fp8", torch::kCUDA, &convert_fp8);
// Gather cache blocks from src_cache to dst.
cache_ops.def(
"gather_cache(Tensor src_cache, Tensor! dst, Tensor block_table, "
"Tensor cu_seq_lens, int batch_size, Tensor? seq_starts) -> ()");
cache_ops.impl("gather_cache", torch::kCUDA, &gather_cache);
}
TORCH_LIBRARY_EXPAND(CONCAT(TORCH_EXTENSION_NAME, _cuda_utils), cuda_utils) {