Commit Graph

5 Commits

Author SHA1 Message Date
Robin Kobus
fffb403125
fix: disable KV cache reuse if using attention sink (#3021)
* fix: disable KV cache reuse if using attention sink

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* fix: disable KV cache reuse if sink bubble

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

* add comment

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>

---------

Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
2025-04-16 03:07:32 +08:00
Chuang Zhu
1c88af1378
feat: use cudaMalloc to allocate kvCache (#3303) 2025-04-08 10:59:14 +08:00
tburt-nv
7a659885e3
chore: remove usernames from comments (#3291)
Signed-off-by: Tyler Burt <195370667+tburt-nv@users.noreply.github.com>
2025-04-05 13:44:28 +08:00
Netanel Haber
da0b0e0ee3
fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983)
* fix variable window size reuse - disable when *min attention window* starts sliding, not max

* isPreCyclic -> isCyclic, and invert logic, for clarity

* getDecoderState()

Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
2025-03-24 22:49:52 +08:00
Kaiyu Xie
9b931c0f63
Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00