Laith Sakka 2e0ad629b0

Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110) ...

Signed-off-by: Laith Sakka <lsakka@meta.com>

2025-11-14 14:11:10 -08:00

..

__init__.py

…

activation_quant_fusion.py

[torch.compile] Enable silu_mul_fp8_quant fusion without custom ops enabled (#27146)

2025-10-22 00:22:39 -04:00

backends.py

[Bugfix] Eliminate tuple inputs to submodules in graph partitioning (#28533)

2025-11-13 15:09:05 -05:00

base_static_graph.py

…

caching.py

…

collective_fusion.py

[PERF] Allreduce fusion. Support torch native matching. Tuning of the thresholds (#24248)

2025-11-10 18:33:11 -05:00

compiler_interface.py

[Bugfix] vLLM should check Inductor config for compile cache enablement status (#27637)

2025-11-05 12:22:44 -05:00

counter.py

…

cuda_graph.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

decorators.py

Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110)

2025-11-14 14:11:10 -08:00

fix_functionalization.py

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

fusion_attn.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

fusion.py

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

fx_utils.py

…

inductor_pass.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

matcher_utils.py

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

monitor.py

[Log] Optimize Startup Log (#26740)

2025-10-24 19:27:04 -04:00

noop_elimination.py

…

partition_rules.py

remove resolve_op_overloads and use splitting_ops directly (#28081)

2025-11-08 01:13:13 +00:00

pass_manager.py

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

piecewise_backend.py

…

post_cleanup.py

…

qk_norm_rope_fusion.py

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

sequence_parallelism.py

…

torch25_custom_graph_pass.py

…

vllm_inductor_pass.py

[Chore] Separate out system utilities from vllm.utils (#27201)

2025-10-22 20:25:25 +00:00

wrapper.py

Avoid bytecode hook and simplify TorchCompileWrapperWithCustomDipatch (#25110)

2025-11-14 14:11:10 -08:00