Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
+4
-6
@@ -23,8 +23,7 @@ async def reset_prefix_cache(
|
||||
reset_running_requests: bool = Query(default=False),
|
||||
reset_external: bool = Query(default=False),
|
||||
):
|
||||
"""
|
||||
Reset the local prefix cache.
|
||||
"""Reset the local prefix cache.
|
||||
|
||||
Optionally, if the query parameter `reset_external=true`
|
||||
also resets the external (connector-managed) prefix cache.
|
||||
@@ -35,6 +34,7 @@ async def reset_prefix_cache(
|
||||
|
||||
Example:
|
||||
POST /reset_prefix_cache?reset_external=true
|
||||
|
||||
"""
|
||||
logger.info("Resetting prefix cache...")
|
||||
|
||||
@@ -46,8 +46,7 @@ async def reset_prefix_cache(
|
||||
|
||||
@router.post("/reset_mm_cache")
|
||||
async def reset_mm_cache(raw_request: Request):
|
||||
"""
|
||||
Reset the multi-modal cache. Note that we currently do not check if the
|
||||
"""Reset the multi-modal cache. Note that we currently do not check if the
|
||||
multi-modal cache is successfully reset in the API server.
|
||||
"""
|
||||
logger.info("Resetting multi-modal cache...")
|
||||
@@ -57,8 +56,7 @@ async def reset_mm_cache(raw_request: Request):
|
||||
|
||||
@router.post("/reset_encoder_cache")
|
||||
async def reset_encoder_cache(raw_request: Request):
|
||||
"""
|
||||
Reset the encoder cache. Note that we currently do not check if the
|
||||
"""Reset the encoder cache. Note that we currently do not check if the
|
||||
encoder cache is successfully reset in the API server.
|
||||
"""
|
||||
logger.info("Resetting encoder cache...")
|
||||
|
||||
@@ -36,6 +36,8 @@ async def pause_generation(
|
||||
"""Pause generation requests to allow weight updates.
|
||||
|
||||
Args:
|
||||
raw_request: The incoming FastAPI request, used to reach the engine
|
||||
client on the app state.
|
||||
mode: How to handle in-flight requests:
|
||||
- ``"abort"``: Abort all in-flight requests immediately (default).
|
||||
- ``"wait"``: Wait for in-flight requests to complete.
|
||||
@@ -43,8 +45,8 @@ async def pause_generation(
|
||||
wait_for_inflight_requests: DEPRECATED. Use ``mode="wait"`` instead.
|
||||
clear_cache: DEPRECATED. Whether to clear KV/prefix caches after
|
||||
draining. Ignored when mode="keep".
|
||||
"""
|
||||
|
||||
"""
|
||||
engine = engine_client(raw_request)
|
||||
|
||||
try:
|
||||
@@ -74,7 +76,6 @@ async def pause_generation(
|
||||
@router.post("/resume")
|
||||
async def resume_generation(raw_request: Request) -> JSONResponse:
|
||||
"""Resume generation after a pause."""
|
||||
|
||||
engine = engine_client(raw_request)
|
||||
|
||||
try:
|
||||
@@ -97,7 +98,6 @@ async def abort_requests(raw_request: Request) -> JSONResponse:
|
||||
|
||||
Empty/missing ``request_ids`` aborts all in-flight requests.
|
||||
"""
|
||||
|
||||
engine = engine_client(raw_request)
|
||||
|
||||
try:
|
||||
@@ -139,7 +139,6 @@ async def abort_requests(raw_request: Request) -> JSONResponse:
|
||||
@router.get("/is_paused")
|
||||
async def is_paused(raw_request: Request) -> JSONResponse:
|
||||
"""Return the current pause status."""
|
||||
|
||||
engine = engine_client(raw_request)
|
||||
|
||||
try:
|
||||
@@ -234,9 +233,12 @@ async def get_world_size(
|
||||
"""Get the world size from the parallel config.
|
||||
|
||||
Args:
|
||||
raw_request: The incoming FastAPI request, used to reach the engine
|
||||
client on the app state.
|
||||
include_dp: If True (default), returns the world size including
|
||||
data parallelism (TP * PP * DP). If False, returns the world
|
||||
size without data parallelism (TP * PP).
|
||||
|
||||
"""
|
||||
parallel_config = engine_client(raw_request).vllm_config.parallel_config
|
||||
if include_dp:
|
||||
|
||||
Reference in New Issue
Block a user