From 8241151f1645a7dd6087c2c5d409bfb69de7d28c Mon Sep 17 00:00:00 2001
From: arthw <14088817+arthw@users.noreply.github.com>
Date: Sat, 14 Sep 2024 09:01:05 +0800
Subject: [PATCH 1/2] set context default to avoid memory issue, update guide

---
 docs/backend/SYCL.md        | 8 ++++++++
 examples/sycl/run-llama2.sh | 7 ++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/docs/backend/SYCL.md b/docs/backend/SYCL.md
index e3b9572cc..ff896af53 100644
--- a/docs/backend/SYCL.md
+++ b/docs/backend/SYCL.md
@@ -636,6 +636,14 @@ use 1 SYCL GPUs: [0] with Max compute units:512
 
   It's same for other projects including llama.cpp SYCL backend.
 
+- Meet issue: `Native API failed. Native API returns: -6 (PI_ERROR_OUT_OF_HOST_MEMORY) -6 (PI_ERROR_OUT_OF_HOST_MEMORY)` or `failed to allocate SYCL0 buffer`
+
+  Device Memory is not enough.
+
+  |Reason|Solution|
+  |-|-|
+  |Default Context is too big. It leads to more memory usage.|Set `-c 8192` or smaller value.|
+  |Model is big and require more memory than device's.|Choose smaller quantized model, like Q5 -> Q4;<br>Use more than one devices to load model.|
 
 ### **GitHub contribution**:
 Please add the **[SYCL]** prefix/tag in issues/PRs titles to help the SYCL-team check/address them without delay.
diff --git a/examples/sycl/run-llama2.sh b/examples/sycl/run-llama2.sh
index a8cf0aa64..3b9ba3b2d 100755
--- a/examples/sycl/run-llama2.sh
+++ b/examples/sycl/run-llama2.sh
@@ -11,16 +11,17 @@ source /opt/intel/oneapi/setvars.sh
 #ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
 
 INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
-MODEL_FILE=llama-2-7b.Q4_0.gguf
+MODEL_FILE=models/llama-2-7b.Q4_0.gguf
 NGL=33
+CONEXT=8192
 
 if [ $# -gt 0 ]; then
     GGML_SYCL_DEVICE=$1
     echo "use $GGML_SYCL_DEVICE as main GPU"
     #use signle GPU only
-    ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -mg $GGML_SYCL_DEVICE -sm none
+    ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT} -mg $GGML_SYCL_DEVICE -sm none
 
 else
     #use multiple GPUs with same max compute units
-    ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0
+    ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT}
 fi

From a6a8f8d09c8e27a70926d8a52016ce8f49d954dd Mon Sep 17 00:00:00 2001
From: Neo Zhang Jianyu <jianyu.zhang@intel.com>
Date: Tue, 17 Sep 2024 16:25:43 +0800
Subject: [PATCH 2/2] Update docs/backend/SYCL.md

Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com>
---
 docs/backend/SYCL.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/backend/SYCL.md b/docs/backend/SYCL.md
index ff896af53..bc266f7d8 100644
--- a/docs/backend/SYCL.md
+++ b/docs/backend/SYCL.md
@@ -636,7 +636,7 @@ use 1 SYCL GPUs: [0] with Max compute units:512
 
   It's same for other projects including llama.cpp SYCL backend.
 
-- Meet issue: `Native API failed. Native API returns: -6 (PI_ERROR_OUT_OF_HOST_MEMORY) -6 (PI_ERROR_OUT_OF_HOST_MEMORY)` or `failed to allocate SYCL0 buffer`
+- Meet issue: `Native API failed. Native API returns: -6 (PI_ERROR_OUT_OF_HOST_MEMORY) -6 (PI_ERROR_OUT_OF_HOST_MEMORY) -999 (UNKNOWN PI error)` or `failed to allocate SYCL0 buffer`
 
   Device Memory is not enough.