refactor: remove devices related gflags.

docs/src/content/docs/en/cli_reference.md

@@ -6,6 +6,8 @@ sidebar:
 
 xLLM uses gflags to manage service startup parameters. `--model <PATH>` is the only required flag. When `--config_json_file` is used, values in the JSON file override command-line flag values. The tables below are grouped by the Config classes in `/xllm/core/framework/config`, with one Config per section. The `ConfigJsonUtils` section contains the common JSON config-file flags.
 
+> **Device selection**: xLLM no longer provides `--devices` / `--device_id` / `--draft_devices`. The devices to run on are determined by the visible-device mask environment variables (`ASCEND_RT_VISIBLE_DEVICES` for NPU, `CUDA_VISIBLE_DEVICES` for NVIDIA, `MLU_VISIBLE_DEVICES` for Cambricon, `HIP_VISIBLE_DEVICES` for DCU, `MUSA_VISIBLE_DEVICES` for Moore Threads). Each process uses all of its visible devices: a single-card process exposes one card, while single-process multi-card exposes several. The draft model always uses the same devices as the target model.
+
 ## ConfigJsonUtils
 
 | Parameter | Type | Default | Description |
@@ -37,8 +39,6 @@ xLLM uses gflags to manage service startup parameters. `--model <PATH>` is the o
 | `model` | `string` | `""` | Hugging Face model name or model path. |
 | `backend` | `string` | `""` | Backend model type: `llm` for text-only models, `vlm` for multimodal models, or `dit` for diffusion models. |
 | `task` | `string` | `"generate"` | Model task, for example `generate`, `embed`, or `mm_embed`. |
-| `devices` | `string` | `""` | Deprecated; use `device_id` instead. Devices used by the current process, for example `npu:0` or `npu:0,npu:1`. |
-| `device_id` | `int32` | `-1` | Device id to run the model on, for example `0`. |
 | `limit_image_per_prompt` | `int32` | `8` | Maximum number of images per prompt. Only applies to multimodal models. |
 | `max_encoder_cache_size` | `int64` | `0` | Maximum GPU/NPU memory size in MB for the encoder cache per worker. `0` disables the encoder cache. |
 | `reasoning_parser` | `string` | `""` | Reasoning parser, for example `auto`, `glm45`, `glm47`, `glm5`, `qwen3`, `qwen35`, or `deepseek-r1`. |
@@ -181,7 +181,6 @@ xLLM uses gflags to manage service startup parameters. `--model <PATH>` is the o
 | Parameter | Type | Default | Description |
 |:----------|:-----|:--------|:------------|
 | `draft_model` | `string` | `""` | Draft model path. See [MTP](/en/features/mtp/) for MTP usage. |
-| `draft_devices` | `string` | `""` | Devices used by the draft model, for example `npu:0` or `npu:0,npu:1`. If omitted, uses the target model devices when speculative decoding is enabled. |
 | `num_speculative_tokens` | `int32` | `0` | Number of speculative tokens generated per speculative decoding step. |
 | `speculative_algorithm` | `string` | `"MTP"` | Speculative decoding algorithm. Supported values: `MTP`, `Eagle3`, `Suffix`, `DFlash`. |
 | `speculative_suffix_cache_max_depth` | `int32` | `64` | Maximum suffix-tree depth for suffix speculative decoding. |

docs/src/content/docs/en/cookbook/autoregressive_models/deepseek/deepseek_v4.md

@@ -131,20 +131,17 @@ MASTER_NODE_ADDR="11.87.49.110:10015"
 LOCAL_HOST="11.87.49.110"
 # Service Port
 START_PORT=18994
-START_DEVICE=0
 LOG_DIR="logs"
 NNODES=8
 
 for (( i=0; i<$NNODES; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/node_$i.log"
   nohup $XLLM_PATH -model-id ds \
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \
@@ -166,7 +163,6 @@ done
 
     # Variables required when MTP is enabled
     # --draft_model=$DRAFT_MODEL_PATH \
-    # --draft_devices="npu:$DEVICE" \
     # --num_speculative_tokens=1 \
 
 # numactl -C xxxxx          NUMA core binding (query with: npu-smi info -t topo)
@@ -179,7 +175,6 @@ done
 #--enable_chunked_prefill   Enable chunked prefill
 #--enable_graph             Enable aclgraph
 #--draft_model              MTP - MTP weights path
-#--draft_devices            MTP - MTP inference device (same as main model)
 #--num_speculative_tokens   MTP - Number of speculative tokens
 ```
 
@@ -206,7 +201,6 @@ export ATB_MATMUL_SHUFFLE_K_ENABLE=0
 MASTER_NODE_ADDR="11.87.49.110:19990"
 LOCAL_HOST="11.87.49.110"
 START_PORT=15890
-START_DEVICE=0
 LOG_DIR="logs"
 NNODES=32
 LOCAL_NODES=16
@@ -215,12 +209,11 @@ unset HCCL_OP_EXPANSION_MODE
 
 for (( i=0; i<$LOCAL_NODES; i++ )); do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i)); LOG_FILE="$LOG_DIR/node_$i.log"
+  LOG_FILE="$LOG_DIR/node_$i.log"
   nohup $XLLM_PATH \
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \
@@ -236,7 +229,6 @@ done
 MASTER_NODE_ADDR="11.87.49.110:19990"
 LOCAL_HOST="11.87.49.111"
 START_PORT=15890
-START_DEVICE=0
 LOG_DIR="logs"
 NNODES=32
 LOCAL_NODES=16
@@ -245,12 +237,11 @@ unset HCCL_OP_EXPANSION_MODE
 
 for (( i=0; i<$LOCAL_NODES; i++ )); do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i)); LOG_FILE="$LOG_DIR/node_$i.log"
+  LOG_FILE="$LOG_DIR/node_$i.log"
   nohup  $XLLM_PATH \
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$((i + LOCAL_NODES)) \

docs/src/content/docs/en/cookbook/autoregressive_models/glm/glm_5.md

@@ -135,7 +135,6 @@ do
   nohup $XLLM_PATH \
     --model $MODEL_PATH \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \
@@ -150,7 +149,6 @@ do
     --communication_backend="hccl" \
     --graph_decode_batch_size_limit=2 \
     --draft_model=$DRAFT_MODEL_PATH \
-    --draft_devices="npu:$DEVICE" \
     --num_speculative_tokens=3 \
     --ep_size=16 \
     --dp_size=2 \
@@ -168,7 +166,6 @@ done
 # --enable_graph             Enable aclgraph. It requires extra memory.
 # --acl_graph_decode_batch_size_limit    Maximum decode batch size for graph capture. It must be <= 32 / (number of speculative tokens + 1).
 # --draft_model              MTP draft-model weight path.
-# --draft_devices            MTP inference device, the same as the main model.
 # --num_speculative_tokens   Number of speculative tokens predicted by MTP.
 ```
 
@@ -211,7 +208,6 @@ do
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \
@@ -226,7 +222,6 @@ do
     --enable_graph=true \
     --acl_graph_decode_batch_size_limit=4 \
     --draft_model=$DRAFT_MODEL_PATH \
-    --draft_devices="npu:$DEVICE" \
     --num_speculative_tokens=3 \
     --ep_size=32 \
     --dp_size=4 \
@@ -258,7 +253,6 @@ do
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$((i + LOCAL_NODES)) \
@@ -273,7 +267,6 @@ do
     --enable_graph=true \
     --acl_graph_decode_batch_size_limit=4 \
     --draft_model=$DRAFT_MODEL_PATH \
-    --draft_devices="npu:$DEVICE" \
     --num_speculative_tokens=3 \
     --ep_size=32 \
     --dp_size=4 \
@@ -442,7 +435,6 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ../xllm-service/build/xllm_service/xllm_m
       --model $MODEL_PATH  --model_id glmmoe \
       --host $LOCAL_HOST \
       --port $PORT \
-      --devices="npu:$DEVICE" \
       --master_node_addr=$MASTER_NODE_ADDR \
       --nnodes=$NNODES \
       --node_rank=$i \
@@ -455,7 +447,6 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ../xllm-service/build/xllm_service/xllm_m
       --enable_chunked_prefill=false \
       --enable_graph=true \
       --draft_model $DRAFT_MODEL_PATH \
-      --draft_devices="npu:$DEVICE" \
       --num_speculative_tokens 1 \
       --tool_call_parser=auto \
       --enable_disagg_pd=true \
@@ -498,7 +489,6 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ../xllm-service/build/xllm_service/xllm_m
       --model $MODEL_PATH  --model_id glmmoe \
       --host $LOCAL_HOST \
       --port $PORT \
-      --devices="npu:$DEVICE" \
       --master_node_addr=$MASTER_NODE_ADDR \
       --nnodes=$NNODES \
       --node_rank=$i \
@@ -511,7 +501,6 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ../xllm-service/build/xllm_service/xllm_m
       --enable_chunked_prefill=false \
       --enable_graph=true \
       --draft_model $DRAFT_MODEL_PATH \
-      --draft_devices="npu:$DEVICE" \
       --num_speculative_tokens 1 \
       --tool_call_parser=auto \
       --enable_disagg_pd=true \

docs/src/content/docs/en/cookbook/autoregressive_models/kimi/kimi2_5.md

@@ -153,10 +153,10 @@ unset HCCL_OP_EXPANSION_MODE
 for (( i=0; i<$LOCAL_NODES; i++ ))do
   PORT=$((START_PORT + i))
   DEVICE=$((START_DEVICE + i));  LOG_FILE="$LOG_DIR/node_$i.log"
-  nohup numactl -C $((DEVICE*40))-$((DEVICE*40+39)) $XLLM_PATH \    --model $MODEL_PATH \
+  nohup numactl -C $((DEVICE*40))-$((DEVICE*40+39)) $XLLM_PATH \
+    --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \
@@ -194,10 +194,10 @@ unset HCCL_OP_EXPANSION_MODE
 for (( i=0; i<$LOCAL_NODES; i++ ))do
   PORT=$((START_PORT + i))
   DEVICE=$((START_DEVICE + i));  LOG_FILE="$LOG_DIR/node_$i.log"
-  nohup numactl -C $((DEVICE*40))-$((DEVICE*40+39)) $XLLM_PATH \    --model $MODEL_PATH \
+  nohup numactl -C $((DEVICE*40))-$((DEVICE*40+39)) $XLLM_PATH \
+    --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$((i + LOCAL_NODES)) \

docs/src/content/docs/en/cookbook/autoregressive_models/minmax/minmax_m2_7.md

@@ -167,20 +167,17 @@ MASTER_NODE_ADDR="10.143.3.204:10015"
 LOCAL_HOST="10.143.3.204"
 # Service port
 START_PORT=18994
-START_DEVICE=0
 LOG_DIR="logs"
 NNODES=16
 
 for (( i=0; i<$NNODES; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/node_$i.log"
   nohup numactl -C $((i*40))-$((i*40+39)) $XLLM_PATH \
     --model $MODEL_PATH \
     --host $LOCAL_HOST \
     --port $PORT \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --node_rank=$i \

docs/src/content/docs/en/cookbook/autoregressive_models/qwen/qwen3_5.md

@@ -91,7 +91,6 @@ export LD_LIBRARY_PATH=/usr/local/libtorch_npu/lib:$LD_LIBRARY_PATH
 source /usr/local/Ascend/ascend-toolkit/set_env.sh
 source /usr/local/Ascend/nnal/atb/set_env.sh
 
-export ASCEND_RT_VISIBLE_DEVICES=14,15
 export ASDOPS_LOG_TO_STDOUT=1
 export ASDOPS_LOG_LEVEL=0
 export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
@@ -120,19 +119,17 @@ DRAFT_MODEL_PATH="/path/to/Qwen3.5-27B-mtp"
 
 MASTER_NODE_ADDR="<master-host>:32764"
 START_PORT=18076
-START_DEVICE=0
 NNODES=2
 
+export ASCEND_RT_VISIBLE_DEVICES=14,15
 export HCCL_IF_BASE_PORT=53433
 
 for (( i=0; i<$NNODES; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/node_$i.log"
   ./xllm/build/xllm/core/server/xllm \
     --model $MODEL_PATH \
-    --devices="npu:$DEVICE" \
     --port $PORT \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
@@ -151,7 +148,6 @@ do
     --max_concurrent_requests=8 \
     --backend llm \
     --draft_model $DRAFT_MODEL_PATH \
-    --draft_devices="npu:$DEVICE" \
     --num_speculative_tokens 3 \
     >> $LOG_FILE 2>&1 &
 done

docs/src/content/docs/en/cookbook/diffusion_models/flux/flux2.md

@@ -114,7 +114,6 @@ export HCCL_IF_BASE_PORT=43432  # HCCL communication base port
 MODEL_PATH="/path/to/flux2/text_encoder/"          # text_encoder path
 MASTER_NODE_ADDR="127.0.0.1:9748"                  # Master node address (must be consistent globally)
 START_PORT=18001                                   # Service starting port
-START_DEVICE=2                                     # Starting logical device ID
 LOG_DIR="log"                                      # Log directory
 NNODES=2                                           # Number of nodes (this script starts 1 process)
 
@@ -123,11 +122,9 @@ mkdir -p $LOG_DIR
 for (( i=0; i<$NNODES; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/mistral_node_$i.log"
   ./build/xllm/core/server/xllm \
     --model $MODEL_PATH \
-    --devices="npu:$DEVICE" \
     --port $PORT \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
@@ -185,21 +182,18 @@ export HCCL_IF_BASE_PORT=43432  # HCCL communication base port
 ```bash
 MASTER_NODE_ADDR="127.0.0.1:8999"                  # Master node address (must be consistent globally)
 START_PORT=18018                                   # Service starting port
-START_DEVICE=4                                     # Starting NPU logical device ID
 LOG_DIR="log"                                      # Log directory
 NNODES=2                                           # Number of nodes (this script starts 2 processes)
 
 for (( i=0; i<2; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/dit_node_$i.log"
   ./build/xllm/core/server/xllm \
     --model="/path/to/flux2/" \
     --max_memory_utilization=0.6 \
     --backend="dit" \
     --tp_size=2 \
-    --devices="npu:$DEVICE" \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --port $PORT \

docs/src/content/docs/en/features/disagg_pd.md

@@ -43,9 +43,8 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ./xllm_master_serving --etcd_addr="127.0.
 - Taking Qwen2-7B as an example  
     - Start Prefill Instance
         ```bash
-        /path/to/xllm --model=Qwen2-7B-Instruct \
+        ASCEND_RT_VISIBLE_DEVICES=0 /path/to/xllm --model=Qwen2-7B-Instruct \
                --port=8010 \
-               --devices="npu:0" \
                --master_node_addr="127.0.0.1:18888" \
                --enable_prefix_cache=false \
                --enable_chunked_prefill=false \
@@ -59,9 +58,8 @@ ENABLE_DECODE_RESPONSE_TO_SERVICE=true ./xllm_master_serving --etcd_addr="127.0.
         ```
     - Start Decode Instance 
         ```bash 
-        /path/to/xllm --model=Qwen2-7B-Instruct \
+        ASCEND_RT_VISIBLE_DEVICES=1 /path/to/xllm --model=Qwen2-7B-Instruct \
                --port=8020 \
-               --devices="npu:1" \
                --master_node_addr="127.0.0.1:18898" \
                --enable_prefix_cache=false \
                --enable_chunked_prefill=false \

docs/src/content/docs/en/features/mtp.md

@@ -94,23 +94,19 @@ MODEL_PATH="/models/DeepSeek-V3"
 DRAFT_MODEL_PATH="/models/DeepSeek-V3-mtp"
 MASTER_NODE_ADDR="127.0.0.1:42123"
 START_PORT=13222
-START_DEVICE=0
 LOG_DIR="log"
 NNODES=16
 
 for (( i=0; i<$NNODES; i++ ))
 do
   PORT=$((START_PORT + i))
-  DEVICE=$((START_DEVICE + i))
   LOG_FILE="$LOG_DIR/node_$i.log"
   nohup ./xllm \
     --model $MODEL_PATH \
-    --devices="npu:$DEVICE" \
     --port $PORT \
     --master_node_addr=$MASTER_NODE_ADDR \
     --nnodes=$NNODES \
     --draft_model $DRAFT_MODEL_PATH \
-    --draft_devices="npu:$DEVICE" \
     --num_speculative_tokens 1 \
     --max_memory_utilization=0.90 \
     --max_tokens_per_batch=10000 \