loopyt 615664e772 fix(triton): delegate the sampler's verify variant instead of asserting ... With MTP on (the default), the sampler is built with rejection sampling for the draft-verification rows, which this backend does not implement. It asserted, so the whole MTP path failed with the triton backend even though 16 of its 20 kernels were ported. It now hands that variant to the default backend and says so once. That is a deliberate delegation rather than a silent fallback: `fused_sample` is exported by this module, so the per-kernel `_FallbackNotice` cannot cover it, and the note has to come from the factory. Verified both ways on 8xH20, same tokens as the pure TileLang run either way: MTP off 20/20 kernels Triton, no fallback notice at all MTP on 16/20 kernels Triton, and exactly five notices -- the four unported MTP kernels plus this delegation, with nothing unaccounted for The remaining MTP work is `remap_draft_topk`, `get_accept_result`, `finalize_verification`, `get_fused_dflash_get_input`, and this rejection variant.		2026-10-22 09:10:45 +08:00
..
asc	initial commit	2026-10-20 12:09:42 +08:00
cuda	initial commit	2026-10-20 12:09:42 +08:00
triton	fix(triton): delegate the sampler's verify variant instead of asserting	2026-10-22 09:10:45 +08:00
__init__.py	initial commit	2026-10-20 12:09:42 +08:00
cache_common.py	feat: add SM90 (Hopper) support for DeepSeek-V4.1 inference	2026-10-21 15:18:56 +08:00
candidate_blocks.py	initial commit	2026-10-20 12:09:42 +08:00
common.py	initial commit	2026-10-20 12:09:42 +08:00
compress.py	initial commit	2026-10-20 12:09:42 +08:00
compute_seqlens_k_zos.py	initial commit	2026-10-20 12:09:42 +08:00
conftest.py	initial commit	2026-10-20 12:09:42 +08:00
dflash_copy.py	initial commit	2026-10-20 12:09:42 +08:00
dflash.py	initial commit	2026-10-20 12:09:42 +08:00
flash_mla_utils.py	initial commit	2026-10-20 12:09:42 +08:00
fused_sample.py	feat(ops): report fallbacks at use time, and record why the sampler stays put	2026-10-22 08:05:05 +08:00
fused_transform.py	feat: add SM90 (Hopper) support for DeepSeek-V4.1 inference	2026-10-21 15:18:56 +08:00
gather_engram_tokens_zos.py	initial commit	2026-10-20 12:09:42 +08:00
gather_input_ids_zos.py	initial commit	2026-10-20 12:09:42 +08:00
gather.py	initial commit	2026-10-20 12:09:42 +08:00
get_kv_index.py	initial commit	2026-10-20 12:09:42 +08:00
image_embed_ops.py	initial commit	2026-10-20 12:09:42 +08:00
kv_index_cat.py	initial commit	2026-10-20 12:09:42 +08:00
load_paged_kv_cache.py	initial commit	2026-10-20 12:09:42 +08:00
norm.py	initial commit	2026-10-20 12:09:42 +08:00
ops.py	feat(ops): report fallbacks at use time, and record why the sampler stays put	2026-10-22 08:05:05 +08:00
outlier_detection.py	initial commit	2026-10-20 12:09:42 +08:00
prepare_cp_mirror.py	initial commit	2026-10-20 12:09:42 +08:00
prepare_v4_decode_metadata.py	initial commit	2026-10-20 12:09:42 +08:00
random_sampling.py	initial commit	2026-10-20 12:09:42 +08:00
sampler.py	initial commit	2026-10-20 12:09:42 +08:00
schedule_mtp_varlen.py	initial commit	2026-10-20 12:09:42 +08:00
state_cache.py	initial commit	2026-10-20 12:09:42 +08:00
store_kv_cache.py	initial commit	2026-10-20 12:09:42 +08:00
store_mtp_info.py	initial commit	2026-10-20 12:09:42 +08:00
structure_output.py	initial commit	2026-10-20 12:09:42 +08:00
sum_smaller_probs.py	initial commit	2026-10-20 12:09:42 +08:00
swa_index.py	initial commit	2026-10-20 12:09:42 +08:00