Commit Graph
29 Commits
Author SHA1 Message Date
8b5014d3dd [Attention] FA4 integration (#32974)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2026-03-01 23:44:57 +00:00
Lucas WilkinsonandGitHub c7914d30f9 Reapply [Attention][FA3] Update FA3 to include new swizzle optimization (#34043)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-02-11 07:07:56 -08:00
Luka GovedičandGitHub e3bf79ffa0 Revert "[Attention][FA3] Update FA3 to include new swizzle optimization" (#33841) 2026-02-04 19:54:27 -08:00
Lucas WilkinsonandGitHub 2267cb1cfd [Attention][FA3] Update FA3 to include new swizzle optimization (#23465)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-02-03 08:08:47 -08:00
Lucas WilkinsonandGitHub be6a81f31b [chore] Update FA commit (#30460)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-01-07 23:24:18 -08:00
Lucas WilkinsonandGitHub c68c7b403d [BugFix] Fix missing symbol triggering FA2 fallback on Hopper (#29107)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-11-21 13:58:32 -08:00
Matthew BonanniandGitHub 4c23690f43 [Attention] FlashAttention ViT support, make default backend (#28763)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-11-18 20:06:21 -08:00
8cc40f8992 [Attention] Bump FA for removed method (#28429)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-11-14 09:13:37 -08:00
9c84ca8293 [FA/Chore] Bump FA version for FP8 two-level accumulation (#27889)
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2025-11-10 12:06:04 -08:00
Lucas WilkinsonandGitHub 9f020f4f31 [BugFix] Fix failing gemma-3-1b-it test: test_lm_eval_accuracy_v1_engine[google/gemma-3-1b-it] (#27111)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-10-18 12:44:39 -06:00
Ming YangandGitHub 3b736e1c38 [Attention][DCP] Support DCP with query length > 1 (MTP) with FA3 (#25049)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-10-09 08:06:29 -07:00
Lucas WilkinsonandGitHub 418d111f8c [FA/Chore] Bump vllm-flash-attention (#25537)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-10-02 11:06:14 -04:00
402759d472 [Attention] FlashAttn MLA (#14258)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
2025-09-04 02:47:59 -07:00
Lucas WilkinsonandGitHub 292084e72a [BugFix] Fix for IMA in FA3 varlen combine (#22967)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-08-17 08:52:04 -07:00
Lucas WilkinsonandGitHub 177e55e3bd [Attention] FA3 Attention Sinks Perf Boost (#22478)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-08-15 17:41:07 -04:00
Thomas ParnellandGitHub bd875d2eb7 [Bugfix] Update FA commit hash (#22546)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-08-08 16:10:25 -07:00
Lucas WilkinsonandGitHub 2cb6ef8996 [BugFix] Fix FA2 RuntimeError when sinks is provided (#22365)
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
2025-08-06 08:03:03 -07:00
Woosuk KwonandGitHub e3c876dca3 Upgrade FA3 for attention sink (#22313)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-05 21:36:21 -07:00
Woosuk KwonandGitHub 8acb4badee [CUDA graphs] Enable full cuda graphs with FA3 AoT scheduling (#20301)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-01 09:07:36 -07:00
Eli UriegasandGitHub 0d06b533a0 cmake: Update vllm_flash_attn for vllm_kernels (#20032)
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
2025-06-24 22:44:10 +00:00
Lucas WilkinsonandGitHub a045b7e89a [Perf] Improve/Fix-regression for FA3 in High QPS regimes (#19463)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-06-24 13:09:01 -04:00
Lucas WilkinsonandGitHub 07334959d8 [Wheel Size] Only build FA2 8.0+PTX (#19336) 2025-06-17 12:32:49 +09:00
Luka GovedičandGitHub a3896c7f02 [Build] Fixes for CMake install (#18570) 2025-05-27 20:49:24 -04:00
b22980a1dc [Perf]Optimize rotary_emb implementation to use Triton operator for improved inference performance (#16457)
Signed-off-by: cynthieye <yexin93@qq.com>
Co-authored-by: MagnetoWang <magnetowang@outlook.com>
2025-04-25 14:52:28 +08:00
Lucas WilkinsonandGitHub 41ca7eb491 [Attention] FA3 decode perf improvement - single mma warp group support for head dim 128 (#16864)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-04-24 20:12:21 -07:00
Lucas WilkinsonandGitHub 183dad7a85 [Attention] Update to lastest FA3 code (#13111)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-04-17 15:14:07 -07:00
Mickaël SeznecandGitHub a597a57595 [Attention] Flash Attention 3 - fp8 (#14570)
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
2025-03-20 01:14:20 -04:00
Pavani MajetyandGitHub ed6ea06577 [Hardware] Update the flash attn tag to support Blackwell (#14244) 2025-03-05 22:01:37 -08:00
Lucas WilkinsonandGitHub f95903909f [Kernel] FlashMLA integration (#13747)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-02-27 10:35:08 +08:00