release: update xllm release version to v0.7.1.

Author: JimHsiung

README.md

@@ -120,22 +120,22 @@ Supported models list:
 First, download the image we provide:
 ```bash
 # A2 x86
-docker pull xllm/xllm-ai:xllm-dev-hb-rc2-x86
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 # A2 arm
-docker pull xllm/xllm-ai:xllm-dev-hb-rc2-arm
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-arm
 # A3 arm
-docker pull xllm/xllm-ai:xllm-dev-hc-rc2-arm
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hc-rc2-arm
 # or
 # A2 x86
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hb-rc2-x86
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 # A2 arm
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hb-rc2-arm
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-arm
 # A3 arm
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hc-rc2-arm
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hc-rc2-arm
 ```
 Then create the corresponding container:
 ```bash
-sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host  --device=/dev/davinci0  --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -v /var/queue_schedule:/var/queue_schedule -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi -v /usr/local/sbin/:/usr/local/sbin/ -v /var/log/npu/conf/slog/slog.conf:/var/log/npu/conf/slog/slog.conf -v /var/log/npu/slog/:/var/log/npu/slog -v /export/home:/export/home -w /export/home -v ~/.ssh:/root/.ssh  -v /var/log/npu/profiling/:/var/log/npu/profiling -v /var/log/npu/dump/:/var/log/npu/dump -v /home/:/home/  -v /runtime/:/runtime/ -v /etc/hccn.conf:/etc/hccn.conf xllm/xllm-ai:xllm-dev-hb-rc2-x86
+sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host  --device=/dev/davinci0  --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -v /var/queue_schedule:/var/queue_schedule -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi -v /usr/local/sbin/:/usr/local/sbin/ -v /var/log/npu/conf/slog/slog.conf:/var/log/npu/conf/slog/slog.conf -v /var/log/npu/slog/:/var/log/npu/slog -v /export/home:/export/home -w /export/home -v ~/.ssh:/root/.ssh  -v /var/log/npu/profiling/:/var/log/npu/profiling -v /var/log/npu/dump/:/var/log/npu/dump -v /home/:/home/  -v /runtime/:/runtime/ -v /etc/hccn.conf:/etc/hccn.conf xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 ```
 
 Install official repo and submodules：

README_zh.md

@@ -115,22 +115,22 @@ xLLM 提供了强大的智能计算能力，通过硬件系统的算力优化与
 首先下载我们提供的镜像：
 ```bash
 # A2 x86
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hb-rc2-x86
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 # A2 arm
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hb-rc2-arm
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-arm
 # A3 arm
-docker pull quay.io/jd_xllm/xllm-ai:xllm-dev-hc-rc2-arm
+docker pull quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hc-rc2-arm
 # 或者
 # A2 x86
-docker pull xllm/xllm-ai:xllm-dev-hb-rc2-x86
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 # A2 arm
-docker pull xllm/xllm-ai:xllm-dev-hb-rc2-arm
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-arm
 # A3 arm
-docker pull xllm/xllm-ai:xllm-dev-hc-rc2-arm
+docker pull xllm/xllm-ai:xllm-0.7.1-dev-hc-rc2-arm
 ```
 然后创建对应的容器
 ```bash
-sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host  --device=/dev/davinci0  --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -v /var/queue_schedule:/var/queue_schedule -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi -v /usr/local/sbin/:/usr/local/sbin/ -v /var/log/npu/conf/slog/slog.conf:/var/log/npu/conf/slog/slog.conf -v /var/log/npu/slog/:/var/log/npu/slog -v /export/home:/export/home -w /export/home -v ~/.ssh:/root/.ssh  -v /var/log/npu/profiling/:/var/log/npu/profiling -v /var/log/npu/dump/:/var/log/npu/dump -v /home/:/home/  -v /runtime/:/runtime/ -v /etc/hccn.conf:/etc/hccn.conf xllm/xllm-ai:xllm-dev-hb-rc2-x86
+sudo docker run -it --ipc=host -u 0 --privileged --name mydocker --network=host  --device=/dev/davinci0  --device=/dev/davinci_manager --device=/dev/devmm_svm --device=/dev/hisi_hdc -v /var/queue_schedule:/var/queue_schedule -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/ -v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi -v /usr/local/sbin/:/usr/local/sbin/ -v /var/log/npu/conf/slog/slog.conf:/var/log/npu/conf/slog/slog.conf -v /var/log/npu/slog/:/var/log/npu/slog -v /export/home:/export/home -w /export/home -v ~/.ssh:/root/.ssh  -v /var/log/npu/profiling/:/var/log/npu/profiling -v /var/log/npu/dump/:/var/log/npu/dump -v /home/:/home/  -v /runtime/:/runtime/ -v /etc/hccn.conf:/etc/hccn.conf quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86
 ```
 
 下载官方仓库与模块依赖：

RELEASE.md

@@ -1,3 +1,30 @@
+# Release xllm 0.7.1
+
+## **Major Features and Improvements**
+
+### Model Support
+
+- Support GLM-4.5-Air.
+- Support Qwen3-VL-Moe.
+
+### Feature
+
+- Support scheduler overlap when enable chunked prefill and MTP.
+- Enable multi-process mode when running VLM model.
+- Support AclGraph for GLM-4.5.
+
+### Bugfix
+
+- Reslove core dump of qwen embedding 0.6B.
+- Resolve duplicate content in multi-turn tool call conversations.
+- Support sampler parameters for MTP.
+- Enable MTP and schedule overlap to work simultaneously.
+- Resolve google.protobuf.Struct parsing failures which broke tool_call and think toggle functionality.
+- Fix the precision issue in the Qwen2 model caused by model_type is not be assigned.
+- Fix core dump of GLM 4.5 when enable MTP.
+- Temporarily use heap allocation for VLM backend.
+- Reslove core dump of stream chat completion request for VLM.
+
 # Release xllm 0.7.0
 
 ## **Major Features and Improvements**

cibuild/build_npu.sh

@@ -6,7 +6,7 @@ function error() {
   exit 1
 }
 
-IMAGE="quay.io/jd_xllm/xllm-ai:xllm-dev-hb-rc2-x86"
+IMAGE="quay.io/jd_xllm/xllm-ai:xllm-0.7.1-dev-hb-rc2-x86"
 
 RUN_OPTS=(
   --rm

version.txt

@@ -1 +1 @@
-0.7.0
+0.7.1