ray_chan
/
TileOPs-Metax
forked from ccf-ai-infra/TileOPs-Metax
1
0
Fork 1
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
TileOPs-Metax/tileops/kernels
History
ray24777 da567b4239 refactor(quant_swiglu): drop stage-profiling variants and their scripts 
Remove the `stage=` builder parameter, the read_only/read_shared/read
probe branches, the _block_sum_reduce macro, and stage_kernel() from the
fused SwiGLU + per-channel FP8-cast kernel.  These existed only to
attribute fused time to pipeline stages for profiling and had no effect on
the production path; the unconditional kernel body is byte-identical to the
former stage="full".  lru_cache returns to default maxsize=32.  Delete
scripts/profile_quant_swiglu_stages.py and
scripts/quant_swiglu_stage_profile.sh, the only consumers.

Verified: tests/ops/test_quant_swiglu_channel_cast_transpose.py 12 passed
(bit-exact fp8 contract preserved).

Co-Authored-By: Claude <noreply@anthropic.com>
 		2026-08-05 11:56:40 +00:00
..
attention docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
deltanet docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
engram [Fix][Engram] Fix inter-block global memory write-read data race in `EngramGateConvBwdKernel` (#1730) 2026-07-20 16:58:03 +08:00
gated_deltanet docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
gla docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
grouped_gemm docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
mamba [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
mhc docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
moe docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
norm [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
pool [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
reduction docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
__init__.py feat(quant_swiglu): add fused SwiGLU + per-channel FP8 cast op 2026-08-03 15:28:30 +00:00
bmm.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
buffer_utils.py [Perf][MoE] Grouped-GEMM TMA OOB zero-fill + unpermute out=: eliminate redundant copies; add fair baseline benchmark (#1580) 2026-06-12 17:52:25 +08:00
convolution.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
deltanet_recurrence.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
dropout.py [Refactor] Rename base modules to <module>_base.py convention (#950) 2026-04-13 18:13:32 +08:00
elementwise.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
fft.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
fp8_lightning_indexer.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
fp8_quant.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
gated_deltanet_recurrence.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
gemm.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
gemm_maca.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00
gla_recurrence.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
kernel_base.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
online_softmax.py [Feat][Attention] Add H200 WS FP8 Tensor Core GQA kernel support (#1511) 2026-05-21 19:43:41 +08:00
quant_swiglu_channel_cast_transpose.py refactor(quant_swiglu): drop stage-profiling variants and their scripts 2026-08-05 11:56:40 +00:00
rope.py [Chore][Cleanup] repo slimming: dead code, duplicated tests/benches, compat shims, file defragmentation (#1764) 2026-07-26 12:59:48 +08:00
topk_selector.py docs: add MetaX C500 summer-camp guide on top of upstream dev 2026-07-28 17:55:09 +00:00