William Zhang 92576488d3 [None][feat] Skip prefetching consolidated safetensors when appropriate (#7013) ... * Why? Some models (e.g. anything produced by Mistral) can have both sharded safetensors and a consolidated safetensor in the same checkpoint directory. In such cases, prefetching both to memory is a waste of time, and memory. * What? This commit skips over consolidated safetensors when they are not the only safetensor file present in the checkpoint directory Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2025-08-25 23:56:21 -04:00
..
dev	Update (#2978)	2025-03-23 16:39:35 +08:00
qa	[None][test] add kv cache size in bench metric and fix failed cases (#7160)	2025-08-26 10:10:02 +08:00
test-db	[None][feat] Skip prefetching consolidated safetensors when appropriate (#7013)	2025-08-25 23:56:21 -04:00
waives.txt	[None][infra] Waive failed tests on main branch (#7201)	2025-08-25 09:04:37 -04:00