Jee Jee Li ee05e8137e [Minor] Bigger overlap for FI AR (#43103) ...

Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>

2026-05-20 21:20:57 -07:00

..

__init__.py

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

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

act_quant_fusion.py

[ROCm][FEAT] AITER Fused Allreduce + RMSNorm (#37646)

2026-05-01 23:07:18 +08:00

allreduce_rms_fusion.py

[Minor] Bigger overlap for FI AR (#43103)

2026-05-20 21:20:57 -07:00

attn_quant_fusion.py

[compile] Allow strings in custom ops without regressing compilation times (#38123)

2026-04-10 07:26:37 +00:00

collective_fusion.py

Add NVFP4 all-gather GEMM fusion for AsyncTP (#41882)

2026-05-10 01:13:22 +00:00

matcher_utils.py

[Aiter][ROCm] RMSNormGated+GroupedQuantFP8 fusion (#40710)

2026-05-14 15:37:09 -04:00

minimax_qk_norm_fusion.py

[Kernel] Porting the TRTLLM minimax_allreduce_rms kernels (#37045)

2026-04-11 00:20:20 +08:00

mla_attn_quant_fusion.py

[compile] mla + group fp8 fusion (#38877)

2026-04-21 23:16:58 -04:00

mla_rope_kvcache_cat_fusion.py

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

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

qk_norm_rope_fusion.py

fused qknorm+rope kernel optimization for SM9.0 (#37376)

2026-04-12 19:58:37 -07:00

rms_quant_fusion.py

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

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

rocm_aiter_fusion.py

[Aiter][ROCm] RMSNormGated+GroupedQuantFP8 fusion (#40710)

2026-05-14 15:37:09 -04:00

rope_kvcache_fusion.py

[compile] Allow strings in custom ops without regressing compilation times (#38123)

2026-04-10 07:26:37 +00:00

sequence_parallelism.py

[Bugfix] Fix SP pass for multimodal models and PP+SP residual handling (#33322)

2026-05-09 19:44:16 -07:00