Select Git revision
a100-mla
abcdabcd987-patch-1
add-qk-sharding-option
add-trtllm
add_test_for_mla
another-bugfix-torch-library
bf16-try
block-load-store-sampling
bugfix-mla
bugfix-no-return
bugfix-torch-library
bugfix-unittest
bump-0.2.2.post1
bump-v0.2.0.post2
bump-v0.2.3
bump-version-0.2.2
byhsu/optimize-rope
cuda-graph-bugfix
decode_maybe_q_rope_offset
deepseek-prefill
different-page-size-mla
dual-pivot-sampling
f32-out
fa3-mla-new
fix-ambiguous-include
fix-mla-header-tvm
fix-mla-kv-0
fix-pdl
fix-sampling-abnormal
fix-split-k-performance-bug
fix-tests-args
github-action-docker-fix
half-mma
hotfix--769
hotfix-756
hotfix-772
hotfix-812
hotfix-block-sparse
improve-jenkins
improve-mla-doc
jenkins
main
mla-16bit-splitk
mla-cuda-graph-test
mla-duplicate-param-set
mla-fa2-split-k
mla-fa3-load-nan
mla-plan-bugfix
mla-prefill-fa2
multiply-scale-at-logits
nandor/type-fix
new-mla-doc
norm-stride
pdl
perf-merge
profiler
reduce-upper-bound-sampling
refactor-attention-updater
remove-triton-dep
renaming-issues
rm-head-64-aot
rope-interleave
slight-fix
slight-upd
specifying-output-in-run-apis
tmp-mla-cuda-cores-no-rope
tvm
tweak-register
unittest-comparing-fa23-deepseek-prefill
update-clera-cache-dir
zhyncs/new
zhyncs/pip
zhyncs/qwen
zhyncs/v0.2.1.post1
v0.0.1
v0.0.2
v0.0.3
v0.0.4
v0.0.5
v0.0.6
v0.0.7
v0.0.8
v0.0.9
v0.1.0
v0.1.1
v0.1.2
v0.1.3
v0.1.4
v0.1.5
v0.1.6
v0.2.0
v0.2.0.post1
v0.2.0.post2
v0.2.1
v0.2.1.post1
v0.2.1.post2
v0.2.2
v0.2.2.post1
v0.2.3