feat: replace gunicorn with hypercorn for http2 (h2c) support (#1211)

Co-authored-by: Siyu Wu <wu.siyu@hotmail.com>

Author: ChieloNewctle

lightllm/server/api_start.py

@@ -10,7 +10,7 @@
 from .embed_cache.manager import start_cache_manager
 from lightllm.utils.log_utils import init_logger
 from lightllm.utils.envs_utils import set_env_start_args, set_unique_server_name, get_unique_server_name
-from lightllm.utils.envs_utils import get_lightllm_gunicorn_time_out_seconds, get_lightllm_gunicorn_keep_alive
+from lightllm.utils.envs_utils import get_lightllm_gunicorn_keep_alive
 from .detokenization.manager import start_detokenization_process
 from .router.manager import start_router_process
 from lightllm.utils.process_check import is_process_active
@@ -333,13 +333,11 @@ def normal_or_p_d_start(args):
         ],
     )
 
-    # 启动 gunicorn
+    # 启动 Hypercorn
     command = [
-        "gunicorn",
+        "hypercorn",
         "--workers",
         f"{args.httpserver_workers}",
-        "--worker-class",
-        "uvicorn.workers.UvicornWorker",
         "--bind",
         f"{args.host}:{args.port}",
         "--log-level",
@@ -349,8 +347,6 @@ def normal_or_p_d_start(args):
         "--error-logfile",
         "-",
         "lightllm.server.api_http:app",
-        "--timeout",
-        f"{get_lightllm_gunicorn_time_out_seconds()}",
         "--keep-alive",
         f"{get_lightllm_gunicorn_keep_alive()}",
     ]
@@ -403,11 +399,9 @@ def pd_master_start(args):
     )
 
     command = [
-        "gunicorn",
+        "hypercorn",
         "--workers",
         "1",
-        "--worker-class",
-        "uvicorn.workers.UvicornWorker",
         "--bind",
         f"{args.host}:{args.port}",
         "--log-level",
@@ -418,8 +412,6 @@ def pd_master_start(args):
         "-",
         "--preload",
         "lightllm.server.api_http:app",
-        "--timeout",
-        f"{get_lightllm_gunicorn_time_out_seconds()}",
         "--keep-alive",
         f"{get_lightllm_gunicorn_keep_alive()}",
     ]
@@ -445,11 +437,9 @@ def config_server_start(args):
     set_env_start_args(args)
 
     command = [
-        "gunicorn",
+        "hypercorn",
         "--workers",
         "1",
-        "--worker-class",
-        "uvicorn.workers.UvicornWorker",
         "--bind",
         f"{args.config_server_host}:{args.config_server_port}",
         "--log-level",
@@ -460,8 +450,6 @@ def config_server_start(args):
         "-",
         "--preload",
         "lightllm.server.config_server.api_http:app",
-        "--timeout",
-        f"{get_lightllm_gunicorn_time_out_seconds()}",
         "--keep-alive",
         f"{get_lightllm_gunicorn_keep_alive()}",
     ]

lightllm/server/req_id_generator.py

@@ -125,10 +125,14 @@ def _find_sibling_processes():
 
     # 查找兄弟进程
     sibling_processes = []
-    for proc in psutil.process_iter(["pid", "name"]):
+    for proc in psutil.process_iter(["pid", "name", "cmdline"]):
         try:
             # 检查是否是兄弟进程（同一父进程且不是当前进程）
             if proc.pid != current_pid and proc.ppid() == parent_process.pid:
+                # 过滤掉 multiprocessing.resource_tracker 进程
+                cmdline = proc.cmdline()
+                if cmdline and "multiprocessing.resource_tracker" in " ".join(cmdline):
+                    continue
                 sibling_processes.append(proc)
         except (psutil.NoSuchProcess, psutil.AccessDenied):
             continue

lightllm/utils/envs_utils.py

@@ -71,10 +71,6 @@ def get_deepep_num_max_dispatch_tokens_per_rank():
     return int(os.getenv("NUM_MAX_DISPATCH_TOKENS_PER_RANK", 256))
 
 
-def get_lightllm_gunicorn_time_out_seconds():
-    return int(os.getenv("LIGHTLMM_GUNICORN_TIME_OUT", 180))
-
-
 def get_lightllm_gunicorn_keep_alive():
     return int(os.getenv("LIGHTLMM_GUNICORN_KEEP_ALIVE", 10))
 

requirements.txt

@@ -79,7 +79,7 @@ ujson==5.10.0
 frozendict==2.4.6
 atomics==1.0.3
 easydict==1.13
-gunicorn==23.0.0
+hypercorn==0.18.0
 flashinfer-python==0.2.4
 sgl-kernel==0.3.7.post1
 httpx==0.28.1