This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
d58da79de76d2c3dfd6799f3355dec9eb8af9b19
vLLM
/
tests
/
models
/
glm5next
T
History
Simon Danielsson
3627a6a124
[ROCm][Perf][GLM-5.3-Flash] Stride-aware decode KDA (
#57979
)
...
Signed-off-by: simondanielsson <
simon.danielsson99@hotmail.com
>
2026-09-30 08:16:29 +00:00
..
__init__.py
[Perf][GLM-5.3-Flash] Decode hot-path cleanups: strided KDA recurrent inputs, NoPE MQA query without concat, no duplicate router GEMM (
#55736
)
2026-09-10 16:28:33 +08:00
test_kda_recurrent.py
[ROCm][Perf][GLM-5.3-Flash] Stride-aware decode KDA (
#57979
)
2026-09-30 08:16:29 +00:00
test_sequence_parallel.py
[Bugfix][GLM-5.3-Flash] Run the dense MLP layers on the sequence-parallel shard (
#58061
)
2026-09-22 21:58:21 +08:00
test_sparse_indexer_topk_dispatch.py
[GLM-5.3-Flash] Route kpool indexer top-k through the shared SparseIndexerTopk dispatcher (
#57546
)
2026-09-20 11:17:59 +00:00