linhaifeng 7901109ea5 [Bugfix] Fix Off-by-one error in _num_tokens_to_min_blocks calculation (#32603) ...

Signed-off-by: linhaifeng <1371675203@qq.com>

2026-01-20 11:13:39 -05:00

..

attention

Revert "[Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#308… (#31617)

2026-01-10 12:39:59 -08:00

core

[CI][Hardware][AMD] Fix test_rotary_embedding_mla_cache_fused (#32408)

2026-01-19 08:25:47 +00:00

helion

[CI] Add Helion as an optional dependency (#32482)

2026-01-19 19:09:56 +00:00

mamba

[Chore] Migrate V0 attention utils (#31891)

2026-01-07 13:44:36 +00:00

moe

[MoE Refactor] Separate Router into OO Classes (#30623)

2026-01-18 11:40:49 -05:00

quantization

[Refactor] Make FP8 Linear Ops use kernel abstraction (#27814)

2026-01-20 14:48:20 +08:00

__init__.py

…

allclose_default.py

…

quant_utils.py

[Bugfix][Hardware][AMD] Consolidate FP8 min/max values helper function (#31106)

2026-01-07 06:55:03 +00:00

test_apply_repetition_penalties.py

…

test_cache_kernels.py

…

test_fla_layernorm_guard.py

…

test_flex_attention.py

…

test_fused_quant_activation.py

[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)

2026-01-08 15:20:49 -08:00

test_onednn.py

…

test_shuffle_rows.py

…

test_top_k_per_row.py

…

utils.py

[Bugfix] Fix Off-by-one error in _num_tokens_to_min_blocks calculation (#32603)

2026-01-20 11:13:39 -05:00