|
|
@@ -63,12 +63,16 @@ B12X_BASE_REF=b58f34eaf978277621efced6678e6713fd7122e4
|
|
|
B12X_PRS="284"
|
|
|
|
|
|
# Deps staging: deps-src.tar.gz (in this dir) carries the pre-fetched build
|
|
|
-# sub-deps. 2026-09-06 re-stage: flash-attention/csrc/cutlass was an empty
|
|
|
-# stub (staging skipped the submodule) — the r18 vllm tree dropped the
|
|
|
-# implicit cutlass include wiring for the FA targets, so the stub broke the
|
|
|
-# FA3 build (sm90_get_smem_store_op_for_accumulator missing in cutlass 4.4.2).
|
|
|
-# Now populated with FA's own pin (vllm pins flash-attention @ f3e1a4f, whose
|
|
|
-# csrc/cutlass gitlink = 62750a2b75c802660e4894434dc55e839f322277, nvidia/cutlass).
|
|
|
+# sub-deps. 2026-09-06 re-stage (two fixes): (1) flash-attention/csrc/cutlass
|
|
|
+# was an empty stub (staging skipped the submodule) — the r18 vllm tree
|
|
|
+# dropped the implicit cutlass include wiring for the FA targets, so the
|
|
|
+# stub broke the FA3 build (sm90_get_smem_store_op_for_accumulator missing
|
|
|
+# in cutlass 4.4.2). Now populated with FA's own pin (vllm pins
|
|
|
+# flash-attention @ f3e1a4f, whose csrc/cutlass gitlink = 62750a2b75c802660e4894434dc55e839f322277,
|
|
|
+# nvidia/cutlass). (2) Same for MSA: fmha_sm100 install needs
|
|
|
+# MSA/python/fmha_sm100/cutlass/include — populated with MSA's own pin
|
|
|
+# (vllm pins vllm-project/MSA @ 087c1618, gitlink eb61c911471867a5fd2466bfd8f29306cea6ebf8).
|
|
|
+# Also purged 23k macOS AppleDouble ._* metadata files from the staging.
|
|
|
|
|
|
# DeepGEMM — fetched by vllm's cmake; pre-cloned (raw-SHA fetches of a
|
|
|
# non-default-branch tip 404 over GitHub's git protocol)
|
