Skip to content

[Experimental][Spec Decode] Port suffix decoding from ArcticInference to vLLM main #24852

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

[Experimental][Spec Decode] Port suffix decoding from ArcticInference to vLLM main #24852

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6610917
port suffix decoding from ArcticInference to vLLM main
zixi-qi Sep 15, 2025
db0a01b
use torch custom op instead of pybind
zixi-qi Sep 15, 2025
a8586c2
Use torch custom op instead of pybind
zixi-qi Sep 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -940,6 +940,24 @@ define_gpu_extension_target(
USE_SABI 3
WITH_SOABI)

#
# _suffix_cache_C extension
#
set(VLLM_SUFFIX_CACHE_EXT_SRC
"csrc/suffix_cache/torch_bindings.cpp"
"csrc/suffix_cache/suffix_tree.cc")

message(STATUS "Enabling suffix_cache extension.")
define_gpu_extension_target(
_suffix_cache_C
DESTINATION vllm
LANGUAGE CXX
SOURCES ${VLLM_SUFFIX_CACHE_EXT_SRC}
COMPILE_FLAGS ${CXX_COMPILE_FLAGS}
USE_SABI 3
WITH_SOABI
)

if(VLLM_GPU_LANG STREQUAL "HIP")
#
# _rocm_C extension
Expand Down
Loading