Gregory Shtrasberg 56c976c1b5 [ROCm] Enable fused_silu_mul_block_quant on ROCm (#38817) ...

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

2026-04-08 11:23:32 -05:00

..

__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] Enable fused_silu_mul_block_quant on ROCm (#38817)

2026-04-08 11:23:32 -05:00

allreduce_rms_fusion.py

[vLLM IR] rework gemma_rms_norm (#39014)

2026-04-07 01:37:00 -07:00

attn_quant_fusion.py

[torch.compile] Refactor Attention Quant Fusion Pass and Remove Boilerplate (#37373)

2026-03-31 14:15:50 -04:00

collective_fusion.py

[Bugfix] Use 'sum' reduction instead of 'avg' in Async TP reduce-scatter (#33088)

2026-02-27 07:06:08 +00:00

matcher_utils.py

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

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

mla_attn_quant_fusion.py

[mla] Support fused FP8/NVFP4 output quantization in MLA attention (#35792) (#36205)

2026-04-02 21:16:11 -04:00

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

rms_quant_fusion.py

[vLLM IR] rework gemma_rms_norm (#39014)

2026-04-07 01:37:00 -07:00

rocm_aiter_fusion.py

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

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

rope_kvcache_fusion.py

[ROCm] AITER fused RoPE+KVCache (#33443)

2026-02-23 19:06:00 -08:00

sequence_parallelism.py

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

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