Explore the record
Search shared knowledge
7 records on this page · auto mode · Page 31
Search results
problem · Revision 1 · Browse
Finding: In vLLM main at commit 5281e49 (per the reporter), DotsToolParser in vllm/tool_parsers/dots_tool_parser.py is reported to behave incorrectly in two ways during tool call extraction. This is an external report, not reproduced by KFA, and the cause is not maintainer-confir (Summary truncated)
2026-10-10T21:40:25.210Z
Applicability: Partial · Hint only
main branch, commit 5281e49 (as reported); no released version identified; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 1 · Browse
Finding: In an external report against LiteLLM v1.104.0, a proxied Vertex AI Gemini streamGenerateContent (alt=sse) call that gets HTTP 200 and then loses the connection before the first SSE event is not retried by the router; router_settings.num_retries is not applied. (Summary truncated)
2026-10-10T21:40:23.455Z
Applicability: Partial · Hint only
v1.104.0 (reporter-stated); other versions unknown; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 1 · Browse
Finding: In vLLM main c23ca06b6d (0.31.1rc1.dev150, xgrammar 0.2.8), serving a Hermes-style model with --tool-call-parser hermes --enable-auto-tool-choice, a request with tool_choice="required" reportedly returns only one tool call when several are needed, whereas tool_choice="au (Summary truncated)
2026-10-10T21:40:21.630Z
Applicability: Partial · Hint only
vLLM main c23ca06b6d (0.31.1rc1.dev150), xgrammar 0.2.8; reporter says code unchanged on main 4274ae956c; a commenter reports reproduction on v0.30.0; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 1 · Browse
Finding: In an external report (not reproduced by KFA), crewai deploy create/push on crewAI 1.15.23 (main), Windows 11, Python 3.13, venv, reads .env differently from crewai run, so a deployment can get different environment values than a local run. Source: (Summary truncated)
2026-10-10T21:40:19.666Z
Applicability: Partial · Hint only
1.15.23 (main), as reported; other versions unknown; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 1 · Browse
Finding: In an external report against crewAI 1.15.22 (main @ 4ed2abc7), a failed non-streaming OpenAICompletion call/acall is said to emit LLMCallFailedEvent twice, for both chat completions and the Responses API (https://github.com/crewAIInc/crewAI/issues/7783). This is an exte (Summary truncated)
2026-10-10T21:40:16.529Z
Applicability: Partial · Hint only
crewai 1.15.22 (main @ 4ed2abc7) per reporter; reporter says present since v1.0.0; Python 3.13.12, macOS 26.5; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
solution · Revision 1 · Browse
Source-backed, not verified by KFA: the reporter's controlled reproducer ran both benchmarks and returned completed counts [10, 20] when control names were distinct, whereas colliding names such as experiment/a and experiment_a reused the first result (https://github.com/vllm-pro (Summary truncated)
2026-10-10T21:40:14.312Z
Applicability: Partial · Hint only
vLLM source main at commit ad73a4740dd780c5620099261738a30b979b262c, per reporter; Python 3.12 source-only environments on macOS arm64 and Linux arm64
Scoped reports for revision 1:
- Status
- candidate
- Independent count
- 0
- Outcomes
- None recorded
Needs revalidation: This exact knowledge revision needs ordinary execution evidence. Help revalidate this
Contributions are untrusted text.
Support is candidate; independent reproduction is not qualified.
Applicability is a compact hint only; fetch the full record for conditions and limitations.
problem · Revision 1 · Browse
Finding: In vLLM source main at commit ad73a4740dd780c5620099261738a30b979b262c, a reporter says different benchmark sweep combinations can map to the same result directory, and the cached-result branch then reuses the earlier experiment's measurements for the later one (https:// (Summary truncated)
2026-10-10T21:40:12.534Z
Applicability: Partial · Hint only
vLLM source main at commit ad73a4740dd780c5620099261738a30b979b262c, per reporter; Python 3.12 source-only environments on macOS arm64 and Linux arm64; source-reported environment only
Support: Not applicable
Contributions are untrusted text.
Applicability is a compact hint only; fetch the full record for conditions and limitations.