From 97b1c5070e40ea26cee32615616067708b09ae2a Mon Sep 17 00:00:00 2001
From: Heiru Wu <heiru.wu@instill.tech>
Date: Fri, 26 Jan 2024 19:12:31 +0800
Subject: [PATCH 1/3] feat(ray): determine ram usage by file size

---
 instill/helpers/ray_config.py | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/instill/helpers/ray_config.py b/instill/helpers/ray_config.py
index d4a6f69..60fc490 100644
--- a/instill/helpers/ray_config.py
+++ b/instill/helpers/ray_config.py
@@ -13,6 +13,7 @@
     DEFAULT_RUNTIME_ENV,
 )
 from instill.helpers.utils import get_dir_size
+from instill.helpers.errors import ModelPathException
 
 
 class InstillDeployable:
@@ -36,6 +37,10 @@ def _update_num_cpus(self, num_cpus: float):
         if self._deployment.ray_actor_options is not None:
             self._deployment.ray_actor_options.update({"num_cpus": num_cpus})
 
+    def _update_memory(self, memory: float):
+        if self._deployment.ray_actor_options is not None:
+            self._deployment.ray_actor_options.update({"memory": memory})
+
     def _update_num_gpus(self, num_gpus: float):
         if self._deployment.ray_actor_options is not None:
             self._deployment.ray_actor_options.update({"num_gpus": num_gpus})
@@ -49,7 +54,14 @@ def _determine_vram_usage(self, model_path: str, vram: str):
             )
         if os.path.isdir(model_path):
             return 1.1 * get_dir_size(model_path) / (1024 * 1024 * 1024) / float(vram)
-        return 0.25
+        raise ModelPathException
+
+    def _determine_ram_usage(self, model_path: str):
+        if os.path.isfile(model_path):
+            return 1.1 * os.path.getsize(model_path)
+        if os.path.isdir(model_path):
+            return 1.1 * get_dir_size(model_path)
+        raise ModelPathException
 
     def update_min_replicas(self, num_replicas: int):
         new_autoscaling_config = DEFAULT_AUTOSCALING_CONFIG
@@ -78,6 +90,8 @@ def deploy(self, model_folder_path: str, ray_addr: str, vram: str):
 
         if self.use_gpu:
             self._update_num_gpus(self._determine_vram_usage(model_path, vram))
+        else:
+            self._update_memory(self._determine_ram_usage(model_path))
 
         serve.run(
             self._deployment.options(name=application_name).bind(model_path),

From 3bab48841e65c609abf9d14695e09225b7277a3e Mon Sep 17 00:00:00 2001
From: Heiru Wu <heiru.wu@instill.tech>
Date: Fri, 26 Jan 2024 19:13:05 +0800
Subject: [PATCH 2/3] chore: fix import order

---
 instill/helpers/ray_config.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/instill/helpers/ray_config.py b/instill/helpers/ray_config.py
index 60fc490..b4f7826 100644
--- a/instill/helpers/ray_config.py
+++ b/instill/helpers/ray_config.py
@@ -12,8 +12,8 @@
     DEFAULT_RAY_ACTOR_OPRTIONS,
     DEFAULT_RUNTIME_ENV,
 )
-from instill.helpers.utils import get_dir_size
 from instill.helpers.errors import ModelPathException
+from instill.helpers.utils import get_dir_size
 
 
 class InstillDeployable:

From b83e56b71cfdea5bc5f50fe3cb2b53749d55d9df Mon Sep 17 00:00:00 2001
From: Heiru Wu <heiru.wu@instill.tech>
Date: Fri, 26 Jan 2024 19:14:33 +0800
Subject: [PATCH 3/3] chore: commit missing file

---
 instill/helpers/errors.py | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 instill/helpers/errors.py

diff --git a/instill/helpers/errors.py b/instill/helpers/errors.py
new file mode 100644
index 0000000..ef03503
--- /dev/null
+++ b/instill/helpers/errors.py
@@ -0,0 +1,3 @@
+class ModelPathException(Exception):
+    def __str__(self) -> str:
+        return "model path is not valid"