[V1] Enable V1 Fp8 cache for FA3 in the oracle (#15191)

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-03-23 18:07:04 -04:00
parent 9c5c81b0da
commit dccf535f8e
9 changed files with 45 additions and 23 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -1157,10 +1157,6 @@ class CacheConfig:
        if self.cache_dtype == "auto":
            pass
        elif self.cache_dtype in ("fp8", "fp8_e4m3", "fp8_e5m2"):
-            if envs.VLLM_USE_V1:
-                raise NotImplementedError(
-                    "V1 does not yet support fp8 KV cache. "
-                    "Set VLLM_USE_V1=0 to enable fp8 kv cache.")
            logger.info(
                "Using fp8 data type to store kv cache. It reduces the GPU "
                "memory footprint and boosts the performance. "