[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Luka Govedič
2026-05-01 23:41:15 -04:00
committed by GitHub
parent 3e49479c4b
commit d58c42e19c
44 changed files with 2833 additions and 779 deletions
+15 -2
View File
@@ -12,10 +12,17 @@ from torch._ops import OpOverload, OpOverloadPacket
from torch.fx._utils import lazy_format_graph_code
from vllm.compilation.passes.fx_utils import find_op_nodes
from vllm.compilation.passes.inductor_pass import InductorPass
from vllm.compilation.passes.inductor_pass import (
InductorPass,
pass_context,
)
from vllm.compilation.passes.ir.inplace_functionalization import (
VllmIRInplaceFunctionalizationPass,
)
from vllm.compilation.passes.pass_manager import with_pattern_match_debug
from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
from vllm.config import VllmConfig, get_current_vllm_config
from vllm.config.utils import Range
from vllm.logger import init_logger
logger = init_logger("vllm.tests.compile.backend")
@@ -53,11 +60,17 @@ class TestBackend:
self.custom_passes = list(passes)
vllm_config = get_current_vllm_config()
compile_config = vllm_config.compilation_config
self.range = Range(1, vllm_config.scheduler_config.max_num_batched_tokens)
# Deepcopy to allow multiple TestBackend instances to use the same VllmConfig
self.inductor_config = deepcopy(compile_config.inductor_compile_config)
self.inductor_config["force_disable_caches"] = True
self.inductor_config["post_grad_custom_post_pass"] = self.post_pass
# Add VllmIRInplaceFunctionalizationPass as pre-grad pass by default
self.inductor_config["pre_grad_custom_pass"] = (
VllmIRInplaceFunctionalizationPass(vllm_config)
)
if debug_dump_path := vllm_config.compile_debug_dump_path():
logger.debug("Dumping depyf output to %s", debug_dump_path)
self.debug_ctx = depyf.prepare_debug(debug_dump_path.as_posix())
@@ -68,7 +81,7 @@ class TestBackend:
self.graph_pre_compile = deepcopy(graph)
from torch._inductor.compile_fx import compile_fx
with self.debug_ctx:
with self.debug_ctx, pass_context(self.range):
return compile_fx(
graph, example_inputs, config_patches=self.inductor_config
)