change file tree (#1859)

Co-authored-by: Chayenne <zhaochenyang@g.ucla.edu>

.github/workflows/deploy-docs.yml

@@ -38,14 +38,8 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
         run: |
           cd docs
-          for nb in *.ipynb; do
-            if [ -f "$nb" ]; then
-              echo "Executing $nb"
-              jupyter nbconvert --to notebook --execute --inplace "$nb" \
-                --ExecutePreprocessor.timeout=600 \
-                --ExecutePreprocessor.kernel_name=python3
-            fi
-          done
+          make clean
+          make compile
 
           make html
           cd _build/html

.github/workflows/execute-notebook.yml

@@ -44,11 +44,5 @@ jobs:
       - name: Execute notebooks
         run: |
           cd docs
-          for nb in *.ipynb; do
-            if [ -f "$nb" ]; then
-              echo "Executing $nb"
+          make clean
+          make compile
\ No newline at end of file
-              jupyter nbconvert --to notebook --execute --inplace "$nb" \
-                --ExecutePreprocessor.timeout=600 \
-                --ExecutePreprocessor.kernel_name=python3
-            fi
-          done
\ No newline at end of file

README.md

@@ -40,13 +40,13 @@ The core features include:
 - **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
 
 ## Install
-See [https://sgl-project.github.io/install.html](https://sgl-project.github.io/install.html)
+See [https://sgl-project.github.io/starts/install.html](https://sgl-project.github.io/starts/install.html)
 
 ## Backend: SGLang Runtime (SRT)
-See [https://sgl-project.github.io/backend.html](https://sgl-project.github.io/backend.html)
+See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
 
 ## Frontend: Structured Generation Language (SGLang)
-See [https://sgl-project.github.io/frontend.html](https://sgl-project.github.io/frontend.html)
+See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
 
 ## Benchmark And Performance
 Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)

docs/Makefile

@@ -12,7 +12,18 @@ BUILDDIR      = _build
 help:
 	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 
-.PHONY: help Makefile
+# New target to compile Markdown and Jupyter Notebook files
+compile:
+	find $(SOURCEDIR) -name '*.ipynb' | while read nb; do \
+		if [ -f "$$nb" ]; then \
+			echo "Executing $$nb"; \
+			jupyter nbconvert --to notebook --execute --inplace "$$nb" \
+				--ExecutePreprocessor.timeout=600 \
+				--ExecutePreprocessor.kernel_name=python3; \
+		fi; \
+	done
+
+.PHONY: help Makefile compile
 
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).

docs/embedding_model.ipynb → docs/backend/embedding_model.ipynb

@@ -30,47 +30,181 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-01T02:47:32.337369Z",
+     "iopub.status.busy": "2024-11-01T02:47:32.337032Z",
+     "iopub.status.idle": "2024-11-01T02:47:59.540926Z",
+     "shell.execute_reply": "2024-11-01T02:47:59.539861Z"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
-      "  warnings.warn(\n",
-      "[2024-10-29 21:07:15] server_args=ServerArgs(model_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='Alibaba-NLP/gte-Qwen2-7B-instruct', chat_template=None, is_embedding=True, host='0.0.0.0', port=30010, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=568040040, constrained_json_whitespace_pattern=None, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:37] server_args=ServerArgs(model_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_path='Alibaba-NLP/gte-Qwen2-7B-instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, context_length=None, device='cuda', served_model_name='Alibaba-NLP/gte-Qwen2-7B-instruct', chat_template=None, is_embedding=True, host='0.0.0.0', port=30010, mem_fraction_static=0.88, max_running_requests=None, max_total_tokens=None, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='lpm', schedule_conservativeness=1.0, tp_size=1, stream_interval=1, random_seed=314021918, constrained_json_whitespace_pattern=None, decode_log_interval=40, log_level='info', log_level_http=None, log_requests=False, show_time_cost=False, api_key=None, file_storage_pth='SGLang_storage', enable_cache_report=False, watchdog_timeout=600, dp_size=1, load_balance_method='round_robin', dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, lora_paths=None, max_loras_per_batch=8, attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='outlines', disable_flashinfer=False, disable_flashinfer_sampling=False, disable_radix_cache=False, disable_regex_jump_forward=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, disable_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_penalizer=False, disable_nan_detection=False, enable_overlap_schedule=False, enable_mixed_chunk=False, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, torchao_config='', enable_p2p_check=False, triton_attention_reduce_in_fp32=False, num_continuous_decode_steps=1)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
       "  warnings.warn(\n",
       "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
-      "  warnings.warn(\n",
-      "[2024-10-29 21:07:20 TP0] Init torch distributed begin.\n",
-      "[2024-10-29 21:07:20 TP0] Load weight begin. avail mem=47.27 GB\n",
-      "[2024-10-29 21:07:21 TP0] lm_eval is not installed, GPTQ may not be usable\n",
-      "INFO 10-29 21:07:22 weight_utils.py:243] Using model weights format ['*.safetensors']\n",
-      "Loading safetensors checkpoint shards:   0% Completed | 0/7 [00:00<?, ?it/s]\n",
-      "Loading safetensors checkpoint shards:  14% Completed | 1/7 [00:00<00:03,  1.65it/s]\n",
-      "Loading safetensors checkpoint shards:  29% Completed | 2/7 [00:01<00:04,  1.02it/s]\n",
-      "Loading safetensors checkpoint shards:  43% Completed | 3/7 [00:03<00:04,  1.24s/it]\n",
-      "Loading safetensors checkpoint shards:  57% Completed | 4/7 [00:05<00:04,  1.47s/it]\n",
-      "Loading safetensors checkpoint shards:  71% Completed | 5/7 [00:07<00:03,  1.62s/it]\n",
-      "Loading safetensors checkpoint shards:  86% Completed | 6/7 [00:08<00:01,  1.64s/it]\n",
-      "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:10<00:00,  1.63s/it]\n",
-      "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:10<00:00,  1.49s/it]\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:43 TP0] Init torch distributed begin.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:44 TP0] Load weight begin. avail mem=47.27 GB\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:44 TP0] lm_eval is not installed, GPTQ may not be usable\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO 10-31 19:47:45 weight_utils.py:243] Using model weights format ['*.safetensors']\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:   0% Completed | 0/7 [00:00<?, ?it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  14% Completed | 1/7 [00:00<00:03,  1.96it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  29% Completed | 2/7 [00:01<00:03,  1.39it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  43% Completed | 3/7 [00:02<00:03,  1.13it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  57% Completed | 4/7 [00:03<00:02,  1.00it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  71% Completed | 5/7 [00:04<00:02,  1.05s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards:  86% Completed | 6/7 [00:05<00:01,  1.09s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00,  1.11s/it]\n",
+      "\r",
+      "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00,  1.01s/it]\n",
       "\n",
-      "[2024-10-29 21:07:32 TP0] Load weight end. type=Qwen2ForCausalLM, dtype=torch.float16, avail mem=32.91 GB\n",
-      "[2024-10-29 21:07:33 TP0] Memory pool end. avail mem=4.56 GB\n",
-      "[2024-10-29 21:07:33 TP0] max_total_num_tokens=509971, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n",
-      "[2024-10-29 21:07:33] INFO:     Started server process [2650986]\n",
-      "[2024-10-29 21:07:33] INFO:     Waiting for application startup.\n",
-      "[2024-10-29 21:07:33] INFO:     Application startup complete.\n",
-      "[2024-10-29 21:07:33] INFO:     Uvicorn running on http://0.0.0.0:30010 (Press CTRL+C to quit)\n",
-      "[2024-10-29 21:07:34] INFO:     127.0.0.1:47812 - \"GET /v1/models HTTP/1.1\" 200 OK\n"
+      "[2024-10-31 19:47:53 TP0] Load weight end. type=Qwen2ForCausalLM, dtype=torch.float16, avail mem=32.91 GB\n",
+      "[2024-10-31 19:47:53 TP0] Memory pool end. avail mem=4.56 GB\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:53 TP0] max_total_num_tokens=509971, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:54] INFO:     Started server process [1552642]\n",
+      "[2024-10-31 19:47:54] INFO:     Waiting for application startup.\n",
+      "[2024-10-31 19:47:54] INFO:     Application startup complete.\n",
+      "[2024-10-31 19:47:54] INFO:     Uvicorn running on http://0.0.0.0:30010 (Press CTRL+C to quit)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:54] INFO:     127.0.0.1:47776 - \"GET /v1/models HTTP/1.1\" 200 OK\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:55] INFO:     127.0.0.1:50344 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
+      "[2024-10-31 19:47:55 TP0] Prefill batch. #new-seq: 1, #new-token: 6, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2024-10-31 19:47:55] INFO:     127.0.0.1:50352 - \"POST /encode HTTP/1.1\" 200 OK\n",
+      "[2024-10-31 19:47:55] The server is fired up and ready to roll!\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "<strong style='color: #00008B;'><br>                            This cell combines server and notebook output. <br>                            <br>                            Typically, the server runs in a separate terminal, <br>                            but we combine the output of server and notebook to demonstrate the usage better.<br>                            <br>                            In our documentation, server output is in gray, notebook output is highlighted.<br>                            </strong>"
+       "<strong style='color: #00008B;'><br><br>                    NOTE: Typically, the server runs in a separate terminal.<br>                    In this notebook, we run the server and notebook code together, so their outputs are combined.<br>                    To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.<br>                    </strong>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -78,16 +212,6 @@
      },
      "metadata": {},
      "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2024-10-29 21:07:34] INFO:     127.0.0.1:41780 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
-      "[2024-10-29 21:07:34 TP0] Prefill batch. #new-seq: 1, #new-token: 6, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
-      "[2024-10-29 21:07:35] INFO:     127.0.0.1:41792 - \"POST /encode HTTP/1.1\" 200 OK\n",
-      "[2024-10-29 21:07:35] The server is fired up and ready to roll!\n"
-     ]
     }
    ],
    "source": [
@@ -118,20 +242,21 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-01T02:47:59.543958Z",
+     "iopub.status.busy": "2024-11-01T02:47:59.543670Z",
+     "iopub.status.idle": "2024-11-01T02:47:59.591699Z",
+     "shell.execute_reply": "2024-11-01T02:47:59.590809Z"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2024-10-28 02:10:30 TP0] Prefill batch. #new-seq: 1, #new-token: 4, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2024-10-28 02:10:31] INFO:     127.0.0.1:48094 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
+      "[2024-10-31 19:47:59 TP0] Prefill batch. #new-seq: 1, #new-token: 4, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
+      "[2024-10-31 19:47:59] INFO:     127.0.0.1:50358 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
      ]
     },
     {
@@ -174,18 +299,21 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-01T02:47:59.594229Z",
+     "iopub.status.busy": "2024-11-01T02:47:59.594049Z",
+     "iopub.status.idle": "2024-11-01T02:48:00.006233Z",
+     "shell.execute_reply": "2024-11-01T02:48:00.005255Z"
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2024-10-28 02:10:31] INFO:     127.0.0.1:48110 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
-      "[2024-10-28 02:10:31 TP0] Prefill batch. #new-seq: 1, #new-token: 6, #cached-token: 0, cache hit rate: 0.00%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
-      "[2024-10-28 02:10:31] INFO:     127.0.0.1:48114 - \"POST /encode HTTP/1.1\" 200 OK\n",
-      "[2024-10-28 02:10:31] The server is fired up and ready to roll!\n",
-      "[2024-10-28 02:10:31 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 21.43%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
-      "[2024-10-28 02:10:31] INFO:     127.0.0.1:48118 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
+      "[2024-10-31 19:47:59 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 21.43%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
+      "[2024-10-31 19:47:59] INFO:     127.0.0.1:50362 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
      ]
     },
     {
@@ -228,13 +356,20 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-01T02:48:00.008858Z",
+     "iopub.status.busy": "2024-11-01T02:48:00.008689Z",
+     "iopub.status.idle": "2024-11-01T02:48:01.872542Z",
+     "shell.execute_reply": "2024-11-01T02:48:01.871573Z"
+    }
+   },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
+      "/home/chenyang/miniconda3/envs/AlphaMeemory/lib/python3.11/site-packages/transformers/utils/hub.py:128: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.\n",
       "  warnings.warn(\n"
      ]
     },
@@ -242,8 +377,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[2024-10-28 02:10:32 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 33.33%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
-      "[2024-10-28 02:10:32] INFO:     127.0.0.1:48124 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
+      "[2024-10-31 19:48:01 TP0] Prefill batch. #new-seq: 1, #new-token: 1, #cached-token: 3, cache hit rate: 33.33%, token usage: 0.00, #running-req: 0, #queue-req: 0\n",
+      "[2024-10-31 19:48:01] INFO:     127.0.0.1:50366 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
      ]
     },
     {
@@ -284,20 +419,15 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[2024-10-28 02:10:32] INFO:     Shutting down\n",
-      "[2024-10-28 02:10:32] INFO:     Waiting for application shutdown.\n",
-      "[2024-10-28 02:10:32] INFO:     Application shutdown complete.\n",
-      "[2024-10-28 02:10:32] INFO:     Finished server process [1188896]\n",
-      "W1028 02:10:32.490000 140389363193408 torch/_inductor/compile_worker/subproc_pool.py:126] SubprocPool unclean exit\n"
-     ]
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-11-01T02:48:01.875204Z",
+     "iopub.status.busy": "2024-11-01T02:48:01.874915Z",
+     "iopub.status.idle": "2024-11-01T02:48:02.193734Z",
+     "shell.execute_reply": "2024-11-01T02:48:02.192158Z"
     }
-   ],
+   },
+   "outputs": [],
    "source": [
     "terminate_process(embedding_process)"
    ]

docs/deploy.py

-# Deploy the documents
+# Deploy the documents	
 
 import os
 from datetime import datetime
 
 
-def run_cmd(cmd):
-    print(cmd)
-    os.system(cmd)
+def run_cmd(cmd):	
+    print(cmd)	
+    os.system(cmd)	
 
 
-run_cmd("cd $DOC_SITE_PATH; git pull")
+run_cmd("cd $DOC_SITE_PATH; git pull")	
 
-# (Optional) Remove old files
-# run_cmd("rm -rf $ALPA_SITE_PATH/*")
+# (Optional) Remove old files	
+# run_cmd("rm -rf $ALPA_SITE_PATH/*")	
 
-run_cmd("cp -r _build/html/* $DOC_SITE_PATH")
+run_cmd("cp -r _build/html/* $DOC_SITE_PATH")	
 
-cmd_message = f"Update {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"
-run_cmd(
-    f"cd $DOC_SITE_PATH; git add .; git commit -m '{cmd_message}'; git push origin main"
-)
+cmd_message = f"Update {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"	
+run_cmd(	
+    f"cd $DOC_SITE_PATH; git add .; git commit -m '{cmd_message}'; git push origin main"	
+)	

docs/index.rst

@@ -15,35 +15,35 @@ The core features include:
    :maxdepth: 1
    :caption: Getting Started
 
-   install.md
-   send_request.ipynb
+   starts/install.md
+   starts/send_request.ipynb
 
 
 .. toctree::
    :maxdepth: 1
    :caption: Backend Tutorial
 
-   openai_api.ipynb
-   backend.md
+   backend/openai_api.ipynb
+   backend/backend.md
 
 
 .. toctree::
    :maxdepth: 1
    :caption: Frontend Tutorial
 
-   frontend.md
+   frontend/frontend.md
 
 
 .. toctree::
    :maxdepth: 1
    :caption: References
 
-   sampling_params.md
-   hyperparameter_tuning.md
-   model_support.md
-   contributor_guide.md
-   choices_methods.md
-   benchmark_and_profiling.md
-   troubleshooting.md
-   embedding_model.ipynb
-   learn_more.md
+   references/sampling_params.md
+   references/hyperparameter_tuning.md
+   references/model_support.md
+   references/contributor_guide.md
+   references/choices_methods.md
+   references/benchmark_and_profiling.md
+   references/troubleshooting.md
+   references/embedding_model.ipynb
+   references/learn_more.md