Jiangyun Zhu d8fc00d623 [torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651) ...

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>

2025-10-03 13:35:56 -07:00

..

__init__.py

[torch.compile] avoid Dynamo guard evaluation overhead (#7898)

2024-08-28 16:10:12 -07:00

activation_quant_fusion.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

backends.py

[V1] address post issues related to #20059 (part 1) (#23046)

2025-10-03 13:35:56 -07:00

base_static_graph.py

[Docs] Fix griffe warning in base_static_graph.py (#25018)

2025-09-17 08:49:19 +00:00

collective_fusion.py

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512)

2025-10-03 13:35:54 -07:00

compiler_interface.py

Add VLLM_ENABLE_INDUCTOR_MAX_AUTOTUNE & VLLM_ENABLE_INDUCTOR_COORDINA… (#25493)

2025-10-03 13:35:54 -07:00

counter.py

[Bugfix] VLLM_V1 supports passing other compilation levels (#19340)

2025-07-29 09:35:58 -04:00

cuda_graph.py

[core] add nccl symmetric memory for all reduce (#24532)

2025-10-03 13:35:54 -07:00

decorators.py

[V1] address post issues related to #20059 (part 1) (#23046)

2025-10-03 13:35:56 -07:00

fix_functionalization.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

fusion_attn.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

fusion.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

fx_utils.py

[torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756)

2025-06-12 08:31:04 -07:00

inductor_pass.py

[Bugfix] Add fake mode around passes (#23349)

2025-08-28 11:25:56 -04:00

monitor.py

[torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651)

2025-10-03 13:35:56 -07:00

noop_elimination.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

pass_manager.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

piecewise_backend.py

[V1] address post issues related to #20059 (part 1) (#23046)

2025-10-03 13:35:56 -07:00

post_cleanup.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

sequence_parallelism.py

[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)

2025-10-03 13:35:53 -07:00

torch25_custom_graph_pass.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

vllm_inductor_pass.py

[torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651)

2025-10-03 13:35:56 -07:00

wrapper.py

[torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651)

2025-10-03 13:35:56 -07:00