stefankoncarevicandAndreas Karatzas 387189c429 [ROCm] Remove redundant AITER fused_qk_rmsnorm probe (avoids config-time HIP init) (#47992) ...

Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>

2026-07-21 22:58:14 -05:00

..

fusion

[Model][Hardware][AMD]: Part 1/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_AITER_FA, and ROCM_AITER_UNIFIED_ATTN (#42749)

2026-07-16 17:39:04 -05:00

ir

Preserve layout-changing clones (#44574)

2026-06-05 20:45:24 -04:00

utility

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

__init__.py

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

fx_utils.py

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

inductor_pass.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

pass_manager.py

[ROCm] Remove redundant AITER fused_qk_rmsnorm probe (avoids config-time HIP init) (#47992)

2026-07-21 22:58:14 -05:00

vllm_inductor_pass.py

[XPU][UT]Enable ut qk_norm_rope_fusion (#42486)

2026-07-01 07:38:03 +00:00