This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
f2bbd575e2be8d901f65e304fcedd05ca7afa31a
vLLM
/
vllm
/
entrypoints
/
openai
/
responses
T
History
Viktor Pus
d5b31c954d
[Bugfix] Account for truncate_prompt_tokens when computing max_tokens (
#41800
)
...
Signed-off-by: Viktor Pus <
viktorpus@tenstorrent.com
>
2026-05-06 16:10:17 +00:00
..
__init__.py
[Refactor] [8/N] to simplify the vLLM openai responsesapi_serving architecture (
#32260
)
2026-01-14 07:26:24 +00:00
api_router.py
Fix Responses JSON schema alias serialization (
#38519
)
2026-04-09 10:50:16 +08:00
context.py
[Bugfix] Pass effective chat template kwargs to reasoning parsers (
#40460
)
2026-04-21 22:17:51 -07:00
harmony.py
[Bugfix] Fix KeyError in parse_response_input for reasoning items with optional content (
#34499
)
2026-03-13 00:13:36 +08:00
protocol.py
[Frontend] Supports resubmitting output items with missing fields in Responses API (
#41355
)
2026-05-05 22:21:33 -04:00
serving.py
[Bugfix] Account for truncate_prompt_tokens when computing max_tokens (
#41800
)
2026-05-06 16:10:17 +00:00
streaming_events.py
[Frontend]Responses API supports Tool/Function calling with streaming with required (
#40700
)
2026-04-27 19:36:58 -07:00
utils.py
fix: Do not make function calls when request has no tools for /v1/responses (
#40314
)
2026-04-20 04:17:30 +00:00