Koushik Dutta d9408ffba3 Triton MLA perf fixes (#33529) ...

Signed-off-by: Koushik Dutta <koushd@gmail.com>
Co-authored-by: root <root@ubuntu-nvidia.localdomain>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

2026-04-02 09:40:01 -04:00

..

mla

Triton MLA perf fixes (#33529)

2026-04-02 09:40:01 -04:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

cpu_attn.py

[CPU] Support gelu act in cpu_fused_moe (#38770)

2026-04-02 14:14:32 +08:00

fa_utils.py

[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007)

2026-03-23 18:31:14 -04:00

flash_attn_diffkv.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

flash_attn.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

flashinfer.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

flex_attention.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

gdn_attn.py

[Bugfix] Use null block (0) for padded block table entries (#35431)

2026-03-30 14:02:51 -07:00

linear_attn.py

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

mamba1_attn.py

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

mamba2_attn.py

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

mamba_attn.py

[Bugfix] Use null block (0) for padded block table entries (#35431)

2026-03-30 14:02:51 -07:00

registry.py

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230)

2026-03-11 19:19:15 +08:00

rocm_aiter_fa.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

rocm_aiter_unified_attn.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

rocm_attn.py

[1/N][Cleanup] Standardize on use of is_quantized_kv_cache (#38659)

2026-04-01 04:08:01 +00:00

short_conv_attn.py

[HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)

2026-03-30 16:47:30 +00:00

tree_attn.py

[Misc] Add float16 to CacheDType (#37199)

2026-03-16 13:24:48 -07:00

triton_attn.py

[Feature] KV cache per-token-head INT8/FP8 quantization (#38378)

2026-04-02 08:13:26 -04:00

utils.py

[Bugfix] Use null block (0) for padded block table entries (#35431)

2026-03-30 14:02:51 -07:00