# glm53-compile-03-fullgraph-optout.patch — let torch.compile split the graph instead
# of failing on a break.
#
# STATUS: WIP — third of three patches in the "compile the GLM trunk" changelist.
# With 01+02+03 the model TRACES, then hits the NEXT blocker (below). The set does not
# yet boot the engine; nothing in scripts/ mounts it.
#
# THE BREAK: with 01+02 mounted the worker dies with
#
#   RuntimeError: Graph breaks are not supported with aot compile.
#   Please use torch.compile(fullgraph=True).
#
# because vllm/compilation/wrapper.py calls torch.compile(..., fullgraph=True, ...) and
# this build has AOT compile on by default (VLLM_USE_AOT_COMPILE). The GLM trunk cannot
# satisfy fullgraph: its indexer metadata path syncs to the host —
#   models/glm5next/amd/sparse_indexer.py:263  int(positions[...].max().item()) + 1
#   models/glm5next/amd/sparse_indexer.py:419  lmax = int(decode_metadata.decode_lens.max().item())
# — and a .item() inside a captured graph is not expressible.
#
# WHAT WAS VERIFIED (in-image, torch 2.11.0+rocm10.0, torch.compile(backend="eager")):
#
#   fullgraph=True   suppress_errors=False  -> RAISE Unsupported
#   fullgraph=True   suppress_errors=True   -> RAISE Unsupported   <-- suppress_errors
#                                                                     does NOT cover breaks
#   fullgraph=False  suppress_errors=False  -> ok   (traceable segments compiled by
#                                                    inductor, the rest runs eagerly;
#                                                    numerics unchanged)
#
# So breaks must be TOLERATED, not suppressed: the traceable mass still fuses. This
# patch makes the fullgraph requirement opt-out via VLLM_COMPILE_FULLGRAPH=0 (default 1,
# so every other model keeps stock behaviour), and the run also needs
# VLLM_USE_AOT_COMPILE=0 because AOT compile refuses breaks outright.
#
# TARGET: vllm/compilation/wrapper.py   (inside the pinned image)
#   base    sha256 969961dca41c78385212e985cfc0c57ef067f4a2d7490c73c658c600a1b95cac
#   patched sha256 732363bb1a1367772f13c60a655c678e7e2e9e56186677b14238f5e84cac31b3
#   (the file already imports os; the patch does not add a second import)
#
# NEXT BLOCKER — NOT FIXED HERE. With 01+02+03 and
# R4D_GLM_COMPILE=1 VLLM_COMPILE_FULLGRAPH=0 VLLM_USE_AOT_COMPILE=0 the trunk traces
# ("Dynamo bytecode transform time: 1.08 s") and then the worker dies during profile_run:
#
#   KeyError: 'in_proj_qkvbfg_a'
#     vllm/models/glm5next/common/model.py:456  in Glm5NextDecoderLayer.forward
#
# `in_proj_qkvbfg_a` is the KDA layer's merged column-parallel projection
# (models/glm5next/common/kda.py:217, called at :407). The key is looked up in a
# dict/mapping that the EAGER path never reaches, so compiling the trunk exposes a
# latent bug in the mHC/KDA wiring rather than a dynamo limitation. Fix that and
# whatever follows before this changelist can boot — then re-measure: the prize is the
# 44 % pointwise mass (see 01), and the frozen-probe log line is the signal that 02 is
# live.
--- a/vllm/compilation/wrapper.py
+++ b/vllm/compilation/wrapper.py
@@ fullgraph opt-out (env VLLM_COMPILE_FULLGRAPH=0) @@
+# FORK-LOCAL (patch: fullgraph opt-out).  torch.compile(fullgraph=True) turns any
+# dynamo graph break into a hard failure; suppress_errors does NOT cover breaks
+# (verified in-image, torch 2.11+rocm10.0).  With VLLM_COMPILE_FULLGRAPH=0 the
+# traceable segments are still compiled by inductor and the untraceable ones run
+# eagerly, which is what a model with device-sync metadata (the GLM-5.3-Flash
+# indexer) needs.  Default 1 keeps stock behaviour for every other model.
+_FULLGRAPH = os.environ.get("VLLM_COMPILE_FULLGRAPH", "1") == "1"
-                fullgraph=True,
+                fullgraph=_FULLGRAPH,