4 people 766b4ae54c [Kimi-K3] Add FlashInfer speculative KDA backend (#54255) ...

Signed-off-by: Duncan Moss <dmoss@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>

2026-10-01 02:28:50 +00:00

..

__init__.py

[ROCm][Perf] Kimi-K3 Shard Latent MoE up-projection for ROCm path (#51253)

2026-08-07 06:11:18 +00:00

test_amd_attn_res.py

[Kimi-K3][AMD] Fuse AttnRes state updates and norms (#50593)

2026-08-04 12:32:13 -04:00

test_amd_kda_chunk.py

[ROCm][Perf] Kimi-K3 Fused kernels for KDA prefill reland (#54038)

2026-09-10 15:37:54 +08:00

test_amd_kda_decode.py

[ROCm][Perf] Enable fused KDA decode on gfx942 (MI325X) (#52293)

2026-08-18 18:01:00 +00:00

test_amd_kda_direct_return.py

[Kimi-K3][AMD] Return KDA and MLA projection outputs directly (#50592)

2026-09-21 15:44:41 -05:00

test_amd_latent_moe_runner.py

[ROCm][Perf] Kimi-K3 Enable sharded latent MoE up-projection under EP (#54956)

2026-09-28 10:31:29 -04:00

test_amd_mla_direct_return.py

[Kimi-K3][AMD] Return KDA and MLA projection outputs directly (#50592)

2026-09-21 15:44:41 -05:00

test_attn_res.py

[CI][ROCm] Add an MI355 Kimi-K3 unit test group (#58012)

2026-09-23 11:25:51 -05:00

test_aux_attn_res_stream.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_eagle3.py

[CI/Build] Fix Kimi K3 Eagle3 test fixture (#54482)

2026-08-31 03:29:45 +00:00

test_kda_metadata.py

[Perf][MRV2] Reuse Mamba/GDN metadata across KV cache groups (#58762)

2026-09-28 04:36:58 +00:00

test_kda.py

[Kimi-K3] Add FlashInfer speculative KDA backend (#54255)

2026-10-01 02:28:50 +00:00

test_latent_moe_tail.py

[MoE] Defer the TRTLLM-Gen top-k finalize on the modular path (#58635)

2026-09-25 15:38:29 +08:00

test_mla_prefill_context.py

[Attention][MLA] Fuse Kimi-K3 chunked-context K/V packing (#51772)

2026-08-12 22:42:57 -07:00

test_nvidia_kda_direct_return.py

[Kimi-K3][AMD] Return KDA and MLA projection outputs directly (#50592)

2026-09-21 15:44:41 -05:00

test_sequence_parallel.py

[Kimi-K3] Add GEMM-RS for sequence parallelism (#52079)

2026-08-13 09:02:28 -07:00

test_weight_loading.py

[Bugfix] Fix Kimi K3 loading with interleaved weight streams (#53379)

2026-09-08 16:08:51 +02:00