4 people d0975a4b50 [perf] Add gemma RMS AR fusion (#42646) ...

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-06-04 01:33:59 -07:00

..

distributed

[perf] Add gemma RMS AR fusion (#42646)

2026-06-04 01:33:59 -07:00

ir

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

2026-05-01 23:41:15 -04:00

__init__.py

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

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

test_double_aiter_rms_quant_fusion.py

[ROCm][Perf] Fix RMSNorm+Quant fusion for gfx950 (non-fnuz) (#41825)

2026-05-11 15:00:51 -04:00

test_functionalization.py

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

2026-05-01 23:41:15 -04:00

test_fuse_act_padding.py

[CI][ROCm] Remove unsupported cases in test_fusion.py (#38680)

2026-05-14 17:37:18 -04:00

test_fuse_mla_dual_rms_norm.py

[ROCm] Add MLA dual RMS norm fusion (Q, KV) pass for DeepSeek/Kimi-K2 (#39242)

2026-04-20 14:56:27 +00:00

test_fusion_attn.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

test_fusion.py

[ROCm][Critical] Fix the GDN import bug (#43486)

2026-05-23 21:12:58 +00:00

test_mla_attn_quant_fusion.py

[fix] flaky test_mla_attn_quant_fusion.py (#40530)

2026-04-22 06:29:58 +00:00

test_mla_rope_kvcache_cat_fusion.py

[Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA (#40392)

2026-05-11 14:10:50 +00:00

test_noop_elimination.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

test_pass_manager.py

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

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

test_qk_norm_rope_fusion.py

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00

test_rope_kvcache_fusion.py

[Performance][DSR1]: Fused RoPE+KVCache+q_concat for MLA (#40392)

2026-05-11 14:10:50 +00:00

test_scatter_split_replace.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

test_silu_mul_quant_fusion.py

[ROCm][CI] Fix TestSiluMulGroupFp8QuantModel after W8A8 block linear refactor (#39799)

2026-04-25 11:20:59 +09:00

test_split_coalescing.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

test_vllm_fusion_pattern_matcher_pass.py

[CI/Build] Apply ruff formatter to pass pre-commit (#40078)

2026-04-17 08:54:32 +08:00