Commit Graph
11 Commits
Author SHA1 Message Date
Matthew BonanniandOpenAI Codex de9250ac9e [Attention] Enable masked MHA for GLM-5 head dimensions (#53785)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-08-27 21:17:12 +00:00
Matthew BonanniandOpenAI Codex 82ae4164ee [2/N][Attention] Enable masked MHA for sparse MLA prefills (#48770)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-07-31 06:01:24 -07:00
Matthew BonanniandClaude Opus 4.8 c4f5cd60da [1/N] Add dense MHA path for sparse MLA short sequences (#47327)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-14 00:29:56 +00:00
Carl Y eb04c769d3 feat: MLA prefill enable FA4 fp8 output (#43050)
Signed-off-by: Carl You <4531192+carlyou@users.noreply.github.com>
2026-06-16 07:10:59 -07:00
Matthew Bonanni cf567cbc71 [Attention] Improve attention benchmarks: configs and profiling (#39336)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2026-06-12 16:24:25 -04:00
Yongye ZhuandRoger Wang 0d2732dd91 [MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
2026-05-13 23:48:02 -07:00
Wei Zhao a3a51d20e7 [Benchmark] Improvements to attention benchmark script (#37115)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
2026-03-16 22:22:40 +00:00
Matthew Bonanni f444c05c32 [Attention] Use FA4 for MLA prefill (#34732)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2026-03-12 12:10:17 -04:00
f2c47886fd [Attention] Add FlashInfer Sparse MLA backend (#33451)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-02-12 17:21:54 +00:00
Lucas WilkinsonandMatthew Bonanni d0d97e2974 [Misc] Fix up attention benchmarks (#33810)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
2026-02-09 09:42:03 -05:00
Matthew BonanniandClaude e82fa448c4 Add attention benchmarking tools (#26835)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-01-28 00:09:20 +00:00