serverAppConfigs/scripts/patches/glm53-dflash-01-aux-hidden-states.patch

# glm53-dflash-01-aux-hidden-states.patch — give the GLM trunk the EAGLE3 / DFlash2
# auxiliary-hidden-state interface.
#
# STATUS: WIP, and INDEPENDENT of the compile changelist (01-05). It patches the same
# file as glm53-compile-01-model-decorator.patch, so if both are ever applied, apply 01
# first. Not part of the deployed shape.
#
# WHY.  `--speculative-config '{"method":"dflash","model":"/path/to/drafter", ...}'` with
# incoai/GLM-5.3-Flash-DFlash2 is accepted -- the config parses, the drafter loads -- and
# then the worker dies at init with:
#
#     RuntimeError: Model does not support EAGLE3 interface
#
# raised by v1/worker/gpu/spec_decode/eagle/eagle3_utils.py:20 through
# `supports_eagle3(model)` == `isinstance(model, SupportsEagle3)` (a runtime-checkable
# Protocol).  Nothing about the drafter, the method name or the payload is wrong:
# `glm5next` implements neither half of the contract.
#
# THE CONTRACT (read out of this image, not assumed):
#   * DEFINITIVE (v5, after four failed boots): the member set is checked against
#     the INSTANCE the runner calls -- which for GLM-5.3-Flash is
#     Glm5NextForConditionalGeneration, NOT Glm5NextForCausalLM.  The multimodal
#     wrapper wraps the text model as self.language_model
#     (init_vllm_registered_model, architectures=["Glm5NextForCausalLM"],
#     glm5next/common/model.py:1113), and model_runner.py:425 calls
#     set_eagle3_aux_hidden_state_layers(self.model) on the CONDITIONAL.
#     Presence rule (verified in-image with stock typing, python 3.14):
#     isinstance walks ALL __protocol_attrs__ -- members of SupportsEagle3 AND
#     its base SupportsEagleBase (has_own_lm_head, has_own_embed_tokens) -- and
#     getattr_static()s each one off the instance, breaking on the first miss.
#     So BOTH wrappers need all three attributes.
#   * MRO law: INHERITING SupportsEagle3 as a base dies at class creation with
#     "Cannot create a consistent method resolution order (MRO) for bases ..."
#     (GLM's wrappers already carry four/five Protocol-derived bases).  The
#     attribute route avoids the MRO entirely.  Also proven by simulation:
#     the four-base ForCausalLM ordering cannot take SupportsEagle3 in ANY
#     position.
#   * Method placement: without inheriting, the Protocol's default
#     set_aux_hidden_state_layers / get_eagle3_default_aux_hidden_state_layers
#     do not exist on either wrapper, so both are defined explicitly --
#     ForCausalLM unwraps to self.model (the EagleModelMixin trunk, v1's
#     correct bodies), the conditional delegates to self.language_model
#     (the pixtral.py:498 pattern).
#   * interfaces.py:1673-1719 -- for reference, the inherited defaults unwrap
#     `holder = getattr(parent_ref, "model", parent_ref)` and assert
#     `isinstance(holder, EagleModelMixin)`, defaulting to (2, L // 2, L - 3).
#   * eagle3_utils.py:26-31 -- layers come from the spec config when it carries them
#     (this drafter ships target_layer_ids [5, 14, 24, 33, 42]), else from the default.
#   * deepseek_v2.py:1551-1585 and v1/worker/gpu/cudagraph_utils.py:621 -- the trunk
#     appends one tensor per aux layer while looping and returns the TUPLE
#     (hidden_states, aux_hidden_states) only when that list is non-empty.
#
# WHAT IT ADDS for GLM: EagleModelMixin on Glm5NextModel; aux capture in the layer
# loop, where the aux state is the single-stream `hidden_states` ENTERING that layer
# (GLM's loop carries the already-summed single-stream state -- its non-mHC branch
# re-splits `residual = hidden_states` inside the layer -- so this is the equivalent
# of deepseek_v2's `hidden_states + residual`); the conditional tuple return; the
# three SupportsEagle3 member attributes on BOTH wrappers; and the two interface
# methods on both (ForCausalLM: unwrap to trunk; conditional: delegate to
# language_model).
#
# HONEST SCOPE: this makes the interface PRESENT, which is exactly what the engine
# checks -- it does not make drafts GOOD, and per the measured profile it is not a
# decode-speed fix (a verification pass pays pointwise cost proportional to its token
# count, which is why MTP4 measured flat).  It is the prerequisite for driving DFlash2
# on this endpoint at all.
#
# TARGET: vllm/models/glm5next/common/model.py   (inside the pinned image)
#   base    sha256 008eeaa2a07e091465319f86900b5a321d921238723ccbe22e6b9e971e1d2b28
#   patched sha256 bc9913a15c8e7f88e0c36b07bf029b383cc8c2078b58d66dc91aa235f8af77f4
#
# APPLY: `patch -p1` from the vllm package root, or bind-mount the patched file over
# site-packages (which is what a scratch-launcher DFLASH_PATCH=1 does).
--- a/vllm/models/glm5next/common/model.py
+++ b/vllm/models/glm5next/common/model.py
@@ -95,6 +95,12 @@
 logger = init_logger(__name__)
 
 
+from vllm.model_executor.models.interfaces import (
+    EagleModelMixin,
+    SupportsEagle3,
+)
+
+
 class Glm5NextMLP(nn.Module):
     def __init__(
         self,
@@ -623,7 +629,7 @@
         )
 
 
-class Glm5NextModel(nn.Module):
+class Glm5NextModel(nn.Module, EagleModelMixin):
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super().__init__()
 
@@ -730,7 +736,14 @@
         if self.is_sequence_parallel:
             hidden_states = sp_shard(hidden_states)
 
-        for layer in self._active_layers:
+        aux_hidden_states: list[torch.Tensor] = []
+        for local_idx, layer in enumerate(self._active_layers):
+            if (getattr(self, "start_layer", 0) + local_idx) in self.aux_hidden_state_layers:
+                # Auxiliary hidden state for EAGLE-3 / DFlash2 drafts: the
+                # single-stream state ENTERING this layer, before its input norm --
+                # the same semantic deepseek_v2 implements by appending
+                # hidden_states + residual at this point in its loop.
+                aux_hidden_states.append(hidden_states)
             hidden_states, residual, post, comb = layer(
                 positions, hidden_states, residual, post, comb
             )
@@ -749,6 +762,8 @@
             hidden_states = sp_all_gather(hidden_states)[:full_num_tokens]
 
         hidden_states = self.norm(hidden_states)
+        if len(aux_hidden_states) > 0:
+            return hidden_states, aux_hidden_states
         return hidden_states
 
     def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
@@ -937,6 +952,10 @@
 class Glm5NextForCausalLM(
     nn.Module, HasInnerState, SupportsPP, MixtureOfExperts, IsHybrid
 ):
+    supports_eagle3: ClassVar[Literal[True]] = True
+    has_own_lm_head: bool = False
+    has_own_embed_tokens: bool = False
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super().__init__()
         self.model_config = vllm_config.model_config
@@ -963,6 +982,14 @@
     def embed_input_ids(self, input_ids: torch.Tensor) -> torch.Tensor:
         return self.model.embed_input_ids(input_ids)
 
+    def set_aux_hidden_state_layers(self, layers: tuple[int, ...]) -> None:
+        # EAGLE-3 / DFlash2 interface: unwrap to the trunk (the EagleModelMixin).
+        self.model.aux_hidden_state_layers = layers
+
+    def get_eagle3_default_aux_hidden_state_layers(self) -> tuple[int, ...]:
+        num_layers = len(self.model.layers)
+        return (2, num_layers // 2, num_layers - 3)
+
     def forward(
         self,
         input_ids: torch.Tensor | None,
@@ -1033,6 +1060,10 @@
 class Glm5NextForConditionalGeneration(
     Glm4vForConditionalGeneration, HasInnerState, IsHybrid, MixtureOfExperts
 ):
+    supports_eagle3: ClassVar[Literal[True]] = True
+    has_own_lm_head: bool = False
+    has_own_embed_tokens: bool = False
+
     # The text model (KDA + dense-MLA + MoE) is a hybrid mamba model. The
     # multimodal wrapper must declare the same interfaces so vLLM treats it as
     # hybrid (auto-aligns mamba/attention block sizes, sizes the mamba state
@@ -1076,6 +1107,13 @@
 
         return Glm5NextForCausalLM.get_mamba_state_copy_func()
 
+    def set_aux_hidden_state_layers(self, layers: tuple[int, ...]) -> None:
+        # EAGLE-3 / DFlash2: delegate to the language model (pixtral.py:498).
+        self.language_model.set_aux_hidden_state_layers(layers)
+
+    def get_eagle3_default_aux_hidden_state_layers(self) -> tuple[int, ...]:
+        return self.language_model.get_eagle3_default_aux_hidden_state_layers()
+
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
         super(Glm4vForConditionalGeneration, self).__init__()
         config = vllm_config.model_config.hf_config