3 people f36b392245 [Bugfix] Report Anthropic prompt cache read statistics ...

Port the cache usage mapping from #241 to current response converters and preserve zero and unavailable counts.

Co-authored-by: Zeaxion <26239880+ChainZeaxion@users.noreply.github.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-03 22:13:48 +08:00

..

anthropic

[Bugfix] Report Anthropic prompt cache read statistics

2026-10-03 22:13:48 +08:00

llm

[Frontend] Split the offline inference APIs and utils. (#43553)

2026-05-26 05:20:24 +00:00

offline_mode

…

openai

fix: strip Responses message transport metadata

2026-09-22 17:00:37 +08:00

pooling

[Feature] Add instruction support for score/rerank chat templates (#42412)

2026-05-14 09:41:22 +08:00

rpc

…

sagemaker

…

serve

[ROCm][CI] Stabilize 400 error return code for invalid schema inputs (#43016)

2026-05-24 10:06:49 +00:00

speech_to_text

[Frontend] Consolidate Speech to Text entrypoints. (#42370)

2026-05-12 07:06:57 +00:00

weight_transfer

[ROCm][CI] Stabilize 400 error return code for invalid schema inputs (#43016)

2026-05-24 10:06:49 +00:00

__init__.py

…

conftest.py

…

test_api_server_process_manager.py

[Bugfix][V1] Fix TOCTOU race causing intermittent EADDRINUSE on multi-API-server DP startup (#42585)

2026-05-26 14:06:00 -07:00

test_chat_utils_failure_lifecycle.py

[Bugfix] Release API and SM70 lifecycle resources

2026-08-31 23:30:42 +08:00

test_chat_utils.py

…

test_cli.py

[Bugfix] Read CLI version from the package

2026-08-15 01:31:20 +08:00

test_context.py

…

test_grpc_health.py

…

test_launch_cli.py

…

test_ssl_cert_refresher.py

…

test_utils.py

…