Chang Su aee62d744b Optimize GPU memory usage in FlashAttentionBackend's strided indexing (#5262) ...

Co-authored-by: ch-wan <cwan39@gatech.edu>

2025-04-11 00:34:17 -07:00

..

triton_ops

Fix shared memory OOM on sm86 GPUs. (#4797)

2025-03-26 10:41:53 -07:00

base_attn_backend.py

fix(typo): fix reply to replay in base_attn_backend.py (#4784)

2025-03-26 00:19:12 -07:00

double_sparsity_backend.py

Misc clean up; Remove the support of jump forward (#4032)

2025-03-03 07:02:14 -08:00

flashattention_backend.py

Optimize GPU memory usage in FlashAttentionBackend's strided indexing (#5262)

2025-04-11 00:34:17 -07:00

flashinfer_backend.py

Fix loading KV quantization scale; Enable modelopt kv cache (#4686)

2025-04-08 09:11:35 -07:00

flashinfer_mla_backend.py

[Revision] Replace enable_flashinfer_mla argument with attention_backend (#5052)

2025-04-05 01:23:02 -07:00

flashmla_backend.py

[Fix] avoid stream sync and torch compile in prefill for fa3 backend (#4932)

2025-03-30 13:53:44 -07:00

torch_native_backend.py

Misc clean up; Remove the support of jump forward (#4032)

2025-03-03 07:02:14 -08:00

triton_backend.py

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

utils.py

Support FlashMLA backend cuda graph (#4514)

2025-03-19 08:25:34 -07:00

vision.py

refactor: bug fixes and refactor for vlm (#4661)

2025-03-22 22:48:49 -07:00