Skip to content

GitLab

"csrc/cuda/fps_kernel.cu" did not exist on "b0f9f81b3394f244925dc95bde5fa37979fed75d"
Unverified Commit 3bf3d011 authored by Chayenne's avatar Chayenne Committed by GitHub
Browse files

Add vlm document (#1866) 


Co-authored-by: default avatarChayenne <zhaochenyang@g.ucla.edu>
parent d86a2d65
Expand all Show whitespace changes
Inline Side-by-side
Showing with 467 additions and 157 deletions
docs/backend/embedding_model.ipynb
View file @ 3bf3d011
...@@ -19,6 +19,7 @@ ...@@ -19,6 +19,7 @@
"## Launch A Server\n", "## Launch A Server\n",
"\n", "\n",
"The following code is equivalent to running this in the shell:\n", "The following code is equivalent to running this in the shell:\n",
"\n",
"```bash\n", "```bash\n",
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n", "python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
" --port 30010 --host 0.0.0.0 --is-embedding\n", " --port 30010 --host 0.0.0.0 --is-embedding\n",
...@@ -44,161 +45,38 @@ ...@@ -44,161 +45,38 @@
"output_type": "stream", "output_type": "stream",
"text": [ "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", "/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" " warnings.warn(\n",
] "[2024-10-31 22:40:37] 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=309155486, 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": [
"[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", "/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", " 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", "/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" " warnings.warn(\n",
] "[2024-10-31 22:40:42 TP0] Init torch distributed begin.\n",
}, "[2024-10-31 22:40:43 TP0] Load weight begin. avail mem=47.27 GB\n",
{ "[2024-10-31 22:40:43 TP0] lm_eval is not installed, GPTQ may not be usable\n",
"name": "stdout", "INFO 10-31 22:40:44 weight_utils.py:243] Using model weights format ['*.safetensors']\n",
"output_type": "stream", "Loading safetensors checkpoint shards: 0% Completed | 0/7 [00:00<?, ?it/s]\n",
"text": [ "Loading safetensors checkpoint shards: 14% Completed | 1/7 [00:00<00:03, 1.97it/s]\n",
"[2024-10-31 19:47:43 TP0] Init torch distributed begin.\n" "Loading safetensors checkpoint shards: 29% Completed | 2/7 [00:01<00:03, 1.40it/s]\n",
] "Loading safetensors checkpoint shards: 43% Completed | 3/7 [00:02<00:03, 1.11it/s]\n",
}, "Loading safetensors checkpoint shards: 57% Completed | 4/7 [00:03<00:03, 1.00s/it]\n",
{ "Loading safetensors checkpoint shards: 71% Completed | 5/7 [00:04<00:02, 1.07s/it]\n",
"name": "stdout", "Loading safetensors checkpoint shards: 86% Completed | 6/7 [00:05<00:01, 1.10s/it]\n",
"output_type": "stream", "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00, 1.12s/it]\n",
"text": [ "Loading safetensors checkpoint shards: 100% Completed | 7/7 [00:07<00:00, 1.02s/it]\n",
"[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", "\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 22:40:51 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" "[2024-10-31 22:40:51 TP0] Memory pool end. avail mem=4.56 GB\n",
] "[2024-10-31 22:40:52 TP0] max_total_num_tokens=509971, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n",
}, "[2024-10-31 22:40:52] INFO: Started server process [1752367]\n",
{ "[2024-10-31 22:40:52] INFO: Waiting for application startup.\n",
"name": "stdout", "[2024-10-31 22:40:52] INFO: Application startup complete.\n",
"output_type": "stream", "[2024-10-31 22:40:52] INFO: Uvicorn running on http://0.0.0.0:30010 (Press CTRL+C to quit)\n",
"text": [ "[2024-10-31 22:40:52] INFO: 127.0.0.1:41676 - \"GET /v1/models HTTP/1.1\" 200 OK\n",
"[2024-10-31 19:47:53 TP0] max_total_num_tokens=509971, max_prefill_tokens=16384, max_running_requests=2049, context_len=131072\n" "[2024-10-31 22:40:53] INFO: 127.0.0.1:41678 - \"GET /get_model_info HTTP/1.1\" 200 OK\n",
] "[2024-10-31 22:40:53 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",
}, "[2024-10-31 22:40:54] INFO: 127.0.0.1:41684 - \"POST /encode HTTP/1.1\" 200 OK\n",
{ "[2024-10-31 22:40:54] The server is fired up and ready to roll!\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"
] ]
}, },
{ {
...@@ -255,8 +133,8 @@ ...@@ -255,8 +133,8 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"[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 22:40:57 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" "[2024-10-31 22:40:57] INFO: 127.0.0.1:51746 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
] ]
}, },
{ {
...@@ -312,8 +190,8 @@ ...@@ -312,8 +190,8 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"[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 22:40:58 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" "[2024-10-31 22:40:58] INFO: 127.0.0.1:51750 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
] ]
}, },
{ {
...@@ -377,8 +255,8 @@ ...@@ -377,8 +255,8 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"[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 22:41:00 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" "[2024-10-31 22:41:00] INFO: 127.0.0.1:51762 - \"POST /v1/embeddings HTTP/1.1\" 200 OK\n"
] ]
}, },
{ {
......
docs/backend/vision_language_model.ipynb 0 → 100644
View file @ 3bf3d011
This diff is collapsed.
docs/index.rst
View file @ 3bf3d011
...@@ -24,6 +24,7 @@ The core features include: ...@@ -24,6 +24,7 @@ The core features include:
:caption: Backend Tutorial :caption: Backend Tutorial
backend/openai_api.ipynb backend/openai_api.ipynb
backend/vision_language_model.ipynb
backend/backend.md backend/backend.md
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment