A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 11:30 UTC
[Misc] Bound NIXL upper bound version (#35495)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Mar 2, 2026 at 09:57 UTC
c212202d936fd772f3c08e1c176f5145e8d37718
1 file changed
+1
-1
requirements/kv_connectors.txt
+1
-1
@@ -1,3 +1,3 @@
1
lmcache >= 0.3.9
2
-nixl >= 0.7.1 # Required for disaggregated prefill
2
+nixl >= 0.7.1, < 0.10.0 # Required for disaggregated prefill
3
mooncake-transfer-engine >= 0.3.8