biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Feature] support sequence parallelism using compilation pass (#16155)

Browse Source 
Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
cascade
2025-04-27 06:29:35 -07:00
committed by GitHub
parent ed7a29d9f8
commit 690fe019f0
21 changed files with 1072 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/compile/test_fusion.py
View File

@@ -77,12 +77,13 @@ def test_fusion_rmsnorm_quant(dtype, hidden_size, num_tokens, eps, static,
vllm_config = VllmConfig(compilation_config=CompilationConfig(
level=CompilationLevel.PIECEWISE, custom_ops=["+rms_norm"]))
vllm_config.compilation_config.pass_config = \
CompilationConfig.PassConfig(enable_fusion=True,
enable_noop=True)
with vllm.config.set_current_vllm_config(vllm_config):
# Reshape pass is needed for the fusion pass to work
config = CompilationConfig.PassConfig(enable_fusion=True,
enable_noop=True)
noop_pass = NoOpEliminationPass(config)
fusion_pass = FusionPass.instance(config)
noop_pass = NoOpEliminationPass(vllm_config)
fusion_pass = FusionPass.instance(vllm_config)
backend = TestBackend(noop_pass, fusion_pass)
model = TestModel(hidden_size, eps, static, cutlass_fp8_enabled)