3 people f51193b9ae [Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291) ...

Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>

2026-07-29 18:54:52 +08:00

..

__init__.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_async_scheduling.py

[XPU] skip UT test_with_ngram_gpu_spec_decoding (#44423)

2026-06-15 08:46:30 +00:00

test_attention_backend_per_kind.py

[Attention] Allow selecting a different attention backend per KV-cache group (#48012)

2026-07-17 15:19:02 -04:00

test_cascade_attention.py

[Hardware][AMD][CI] Fix e2e core test group (#46024)

2026-06-20 02:04:35 -05:00

test_context_length.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_correctness_sliding_window.py

[ROCm][CI] Ensure sliding window tests release GPU memory (#49055)

2026-07-18 20:44:05 +00:00

test_kv_sharing_fast_prefill.py

[Test][XPU] Skip fork in kv_sharing_fast_prefill test on XPU (#47406)

2026-07-06 11:32:26 +08:00

test_mamba_prefix_cache.py

[Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291)

2026-07-29 18:54:52 +08:00

test_min_tokens.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_pooling_chunked_prefill.py

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test_rocm_aiter_custom_ar.py

[ROCm][AITER] Directly Implement AITER Custom All-reduce in CudaCommunicator (#46065)

2026-07-06 12:16:32 +00:00

test_streaming_input.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00