# 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
# on the decode forward:
#
#   KeyError: 'in_proj_qkvbfg_a'
#     model.py:748  Glm5NextModel.forward        hidden_states, residual, post, comb = layer(...)
#     model.py:456  Glm5NextDecoderLayer.forward
#
# `in_proj_qkvbfg_a` is the KDA layer's merged column-parallel projection
# (models/glm5next/common/kda.py:217, called at :407) — and it is also a name in the
# load_weights shard table (model.py:780-785), i.e. a real submodule attribute name,
# not an arbitrary string.
#
# WHERE IT IS THROWN (established 2026-09-30 by reading the full traceback, since the
# report line is inside dynamo-rewritten code): torch/_dynamo keeps a name -> module map
# and looks it up by name — output_graph.py:1259 / :1384 register into `nn_modules`,
# :3000 does `self.nn_modules[node.target]` (a bare-name KeyError when absent), and
# :1225 documents stripping "_buffers[..]/_parameters[..]/_modules[..]" from those
# names. So the compiler is failing to RESOLVE A SUBMODULE BY NAME while tracing the
# GLM decoder layer. Whether the root cause is the fork's module tree (something
# dynamo cannot register statically) or dynamo's own registration is NOT yet settled.
#
# STATUS OF THAT BLOCKER (updated 2026-09-30, after the diagnostics below):
#   * TORCHDYNAMO_VERBOSE=1 adds NO internal stack trace -> it is a plain Python
#     KeyError raised in a callee dynamo INLINED into Glm5NextDecoderLayer.forward
#     (the reported line 456 is that method's `def` line, which is how inlined frames
#     surface).
#   * It is NOT raised from dynamo's four nn_modules lookups: the probe in
#     /home/dank/dynamo-probe wraps three of them and stayed silent over two runs with
#     the probe confirmed installed in the API-server and worker processes.
#   * It is NOT a literal string lookup: the name appears tree-wide only as the KDA
#     layer's attribute (kda.py:217, used at :407) and in the load_weights shard table
#     (model.py:780-785). The four `proj_name = prefix.split(".")[-1]` sites in the
#     quantization utils do compute exactly this bare key, but each is guarded
#     (`if proj_name not in fused_mapping: return`), so none of them can raise it.
#   * It reproduces on every run of this configuration (5 of 5).
# REMAINING INSTRUMENT: name the inlined caller. Either `TORCH_LOGS=+dynamo` on a boot
# and grep the log for the key (dynamo prints inlined frames with source), or wrap the
# inlining candidates in that forward — the mHC CustomOps (hc_pre / hc_post /
# hc_fused_post_pre in layers/mhc.py) and the indexer op — with a KeyError-reporting
# probe. Until that names the caller this is a dynamo-side name-resolution failure.
# NOTE the launcher gotcha that wasted a boot earlier: the scratch launcher now
# preserves ENVARGS (`ENVARGS="${ENVARGS:-}"`), but it previously reset it, silently
# dropping outer env vars.
#
# SECOND BLOCKER, KNOWN AND NOT FATAL IN THIS CONFIG: the indexer's in-forward
# workspace acquisition (patch 05 makes it compiler-opaque) and the fused-norm
# launcher cell (patch 04 removes the call) are real breaks, but with
# VLLM_COMPILE_FULLGRAPH=0 they are tolerated — they only become fatal under
# fullgraph=True, which this trunk can never satisfy anyway.
--- a/vllm/compilation/wrapper.py
+++ b/vllm/compilation/wrapper.py
@@ -19,6 +19,15 @@
 
 logger = init_logger(__name__)
 
+
+# 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"
+
 R = TypeVar("R")
 P = ParamSpec("P")
 
@@ -146,7 +155,7 @@
         with aot_context:
             self._compiled_callable = torch.compile(
                 compiled_ptr,
-                fullgraph=True,
+                fullgraph=_FULLGRAPH,
                 dynamic=False,
                 backend=backend,
                 options=options,