-
ggml: Prevent kv cache quanitization on gpt-oss
frostbyte_neo 发布于
2025-08-05 20:04:03 +00:00 KV cache quantization has a dependency on the flash attention kernel.
We currently cannot use flash attention with gpt-oss as it requires
additional operations.The model definition does not call flash attention, so it works
regardless of the setting but the cache will pick up the
quantization type. This updates the flash attention setting earlier
in the loading flow so that all downstream settings are also set correctly.Fixes: #11671
下载附件