mirror of
https://github.com/deepseek-ai/DeepInfer.git
synced 2026-10-31 08:46:21 +08:00
An edit of mine dropped a `return launch` from `finalize_verification_tl`. The A/B case for that kernel was not re-run, so nothing local objected; the failure surfaced as a TypeError inside the sampler of an end-to-end run, once per rank. The harness now checks that every `*_tl` symbol the selected backend exports is callable, which turns that class of mistake into one line printed before any case executes. Also records where the remaining sixteen kernels actually sit. None of them is unconditionally on the path, but the distribution is lopsided and the document had it backwards in one place: the three `candidate_*` kernels are not merely "off on SM90", they are switched off *by* `PLATFORM.is_sm90` -- and this checkpoint sets `candidate_source_layer_id=20` of 40 layers. On a card where `is_sm90` is False, that is nineteen layers on every step, which is the opposite of optional. Their harder blocker is noted alongside: that path also needs `deep_gemm.fp8_fp4_sparse_mqa_logits`, which is SM100-only, so porting those three alone would buy nothing. The four kernels that no production path reaches are listed as such, so nobody spends an afternoon on them. |
||
|---|---|---|
| .. | ||
| ab_cases.py | ||
| build_vendor.sh | ||
| build.sh | ||
| compare_layers.py | ||
| copy_site_packages.py | ||
| flagtree_triton_probe.py | ||
| format_csrc.sh | ||
| gen_stub.sh | ||
| h20_ask.py | ||
| h20_attn_check.py | ||
| h20_e2e_report.sh | ||
| h20_engram_check.py | ||
| h20_expert_weight_check.py | ||
| h20_index_decode_check.py | ||
| h20_kv_roundtrip.py | ||
| h20_ops_ab.py | ||
| h20_philox_check.py | ||
| h20_quant_check.py | ||
| h20_real_requant_check.py | ||
| h20_recipe_probe.py | ||
| h20_rng_dump.py | ||
| h20_smoke_check.py | ||
| h20_state_check.py | ||
| h20_topk_check.py | ||
| ref_layer_dump.py | ||
| ref_next_token.py | ||
| setup_flagtree_image.sh | ||