Skip to content

Pull requests: tenstorrent/tt-inference-server

New pull request New
55 Open 1,037 Closed
55 Open 1,037 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix Qwen-Image camel casing in ModelNames
#2106 opened Feb 13, 2026 by bgoelTT Loading…
@bgoelTT
2
Add v1 api prefix
#2105 opened Feb 12, 2026 by vpetrovicTT • Draft
2
Ensure Flux readiness on blackhole quietbox devices
#2104 opened Feb 12, 2026 by vpetrovicTT • Draft
1
2
Samt/uv fixed fea qb fix depend
#2102 opened Feb 12, 2026 by stisiTT • Draft
2
Ben/v1
#2101 opened Feb 12, 2026 by bgoelTT • Draft
@bgoelTT
2
Idjuric/test dp2
#2100 opened Feb 12, 2026 by idjuricTT Loading…
2
Dmadic tt/h2d d2h model runner
#2099 opened Feb 12, 2026 by dmadicTT • Draft
Enable Apply Chat Template
#2098 opened Feb 12, 2026 by ljovanovicTT • Draft
Use Whisper DP2 by default
#2097 opened Feb 11, 2026 by idjuricTT Loading…
2
Default LLM benchmarks to target /v1/chat/completions endpoint
#2096 opened Feb 11, 2026 by bgoelTT Loading…
@bgoelTT
4
cpp_server connect vllm e2e
#2092 opened Feb 11, 2026 by knovokmetTT • Draft
9
Convert LLM streaming overhead metric from milliseconds to microseconds
#2075 opened Feb 10, 2026 by Copilot AI • Draft
@dmadicTT
2
Remove TTNN from C++ server Docker image
#2073 opened Feb 10, 2026 by ztorlakTT Loading…
@ztorlakTT
Allow Flux to use inference steps 4
#2062 opened Feb 10, 2026 by vpetrovicTT Loading…
1
4
Implement logic for canceling fine tuning jobs
#2050 opened Feb 9, 2026 by mcupacTT • Draft
1
2
Refactor of eval tests
#2033 opened Feb 6, 2026 by vpetrovicTT • Draft
1
2
Fix build
#2028 opened Feb 6, 2026 by idjuricTT Loading…
another cpp server showcase
#2026 opened Feb 6, 2026 by knovokmetTT • Draft
enable eval forge llm
#2018 opened Feb 5, 2026 by knovokmetTT • Draft
2
Flux motif eval test
#2017 opened Feb 5, 2026 by vpetrovicTT Loading…
2
7
Add support for BH T3K video models
#1988 opened Feb 4, 2026 by fivanovicTT • Draft
1
3
Refactor generation of reports in clients
#1969 opened Feb 2, 2026 by vpetrovicTT • Draft
1
15
Do not log time and telemetry when using critical log level
#1943 opened Jan 29, 2026 by idjuricTT Loading…
2
GPT-OSS evals and RAM fix bug Something isn't working Models CI onboarding Issue for model onboarding on Models CI, has to be triaged by respective model owner teams
#1941 opened Jan 29, 2026 by stisiTT • Draft
@stisiTT
2
Dmadic tt/prefill server poc
#1936 opened Jan 29, 2026 by dmadicTT • Draft
21
ProTip! Mix and match filters to narrow down what you’re looking for.