1
0

Коммит түүх

Эзэн SHA1 Мессеж Огноо
  Ying Zhang cdbbe844b1 minor changes to unpad_input test util func 3 сар өмнө
  Tri Dao 299563626f Fix test with alibi and cache_leftpad 4 сар өмнө
  Tri Dao 751c762c9c Don't specialize for hdim 224 to speed up compilation 4 сар өмнө
  Phil Wang 5f1ae4a34b backwards for softcapping (#1033) 4 сар өмнө
  Tri Dao 40e534a7f6 Implement cache_leftpad 5 сар өмнө
  Tri Dao d0787acc16 Relax dropout_fraction test 5 сар өмнө
  Tri Dao dca6d89da4 Don't support softcap and dropout at the same time 5 сар өмнө
  Tri Dao 81e01efd4b More typo fixes 5 сар өмнө
  Tri Dao 3d41db3e2c Only test backward if there's no softcapping 5 сар өмнө
  Nicolas Patry 8f873cc6ac Implement softcapping. (#1025) 5 сар өмнө
  muoshuosha 6df7e0a02e Fix the varlen deterministic test (#1023) 5 сар өмнө
  cao lei 6a2a16e994 fix typo (#974) 5 сар өмнө
  Grigory Sizov f816dee63c Support unpadded LSE layout (#970) 5 сар өмнө
  Grigory Sizov 2a15840f09 Enable paged attention in varlen forward (#831) 9 сар өмнө
  Tri Dao 2406f28805 Enable headdim 256 backward on consumer GPUs (Ampere, Ada) 9 сар өмнө
  Tri Dao 54e80a3829 Implement page KV cache 10 сар өмнө
  Tri Dao 10dad61277 apply_dropout now takes tensor of rowcol layout 11 сар өмнө
  Tri Dao a7b66ae25a Simplify writing softmax to gmem 11 сар өмнө
  Tri Dao 732654583c Implement deterministic backward (thanks to Meituan) 11 сар өмнө
  Tri Dao 5ab9b3667b Clean up alibi, implement non-causal alibi 1 жил өмнө
  Tri Dao e279bf8ed9 [Gen] Accept cache_batch_idx to index into the KV cache 1 жил өмнө
  Tri Dao 083e8f525f Implement local attention 1 жил өмнө
  Tri Dao 65c234ed90 Don't over-allocate dq_accum in case of varlen 1 жил өмнө
  Tri Dao 2d8ea9a530 Swap seqlen_q and ngroups when seqlen_q=1 (h/t Daniel Haziza) 1 жил өмнө
  Tri Dao 3250ff3d82 Swap seqlen_q, nheads for MQA when seqlen_q=1 for fwd (h/t Daniel H) 1 жил өмнө
  Tri Dao ccbb14f38e Implement rotary embedding in flash_attn_with_kvcache 1 жил өмнө
  Tri Dao 56b7fc6ee0 Simplify the implementation of KVcache attn by appending KV first 1 жил өмнө
  Tri Dao 37c6e05406 Implement flash_attn_with_kvcache 1 жил өмнө
  Tri Dao 0c04943fa2 Require CUDA 11.6+, clean up setup.py 1 жил өмнө
  Tri Dao b1fbbd8337 Implement splitKV attention 1 жил өмнө