Charles Chen 5ae8d286d2 perf(gemma4): single-launch fused router (topk + softmax + scale) (#26502)

2026-06-02 16:00:17 +08:00

..

test_cp_prefix_len_fa3_parity.py

Support batch size > 1 when enable CP (#23269)

2026-05-27 14:11:17 -07:00

test_dsa_indexer.py

[FlashInfer v0.6.10] [RL] [DSv32] [GLM-5] Add --dsa-topk-backend and integrate FlashInfer and pytorch topk (#22851)

2026-05-25 13:08:03 -07:00

test_fp4_moe.py

[kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277)

2026-03-14 16:45:54 +08:00

test_fused_topk_deepseek.py

docs: improve CI and testing documentation (#21202)

2026-03-23 10:48:50 -07:00

test_gemma4_fused_routing.py

perf(gemma4): single-launch fused router (topk + softmax + scale) (#26502)

2026-06-02 16:00:17 +08:00

test_mla_cp_fa3_parity.py

Support batch size > 1 when enable CP (#23269)

2026-05-27 14:11:17 -07:00

test_sm120_flash_mla.py

feat: SM120 (Blackwell Desktop) support for DeepSeek-V4 inference (#24692)

2026-06-01 14:05:20 -07:00

test_sm120_paged_mqa_logits.py

feat: SM120 (Blackwell Desktop) support for DeepSeek-V4 inference (#24692)

2026-06-01 14:05:20 -07:00