{"schema_version":"onlylabs.public_signal.v1","title":"Baseten Repo: basetenlabs/basetenkenizer","description":"Baseten repo signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6","json_url":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6/signal.json","generated_at":"2026-07-28T20:40:09.204Z","evidence_latest_fetched_at":"2026-07-28T07:02:01.270308+00:00","signal_first_seen_at":"2026-07-28T07:00:36.283493+00:00","org":{"slug":"baseten","name":"Baseten","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/baseten","dossier_json_url":"https://onlylabs.fyi/labs/baseten/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6","signal_json":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6/signal.json","source":"https://github.com/basetenlabs/basetenkenizer","lab_dossier":"https://onlylabs.fyi/labs/baseten","lab_dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis":"https://onlylabs.fyi/analysis/baseten","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":null},"answer_pack":{"answer":"Baseten published basetenlabs/basetenkenizer (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo basetenlabs/basetenkenizer · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","signal_desk":"repos","source_context":{"source_url":"https://github.com/basetenlabs/basetenkenizer","source_host":"github.com","occurred_at":"2026-07-27T03:54:34+00:00","first_seen_at":"2026-07-28T07:00:36.283493+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Baseten","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"basetenlabs/basetenkenizer","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"1","source":"traction"},{"label":"Watch term","value":"Model card","source":"model"},{"label":"Watch term","value":"Infrastructure","source":"evidence"},{"label":"Watch term","value":"Safety and alignment","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/basetenlabs/basetenkenizer"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-07-28T07:02:01.270308+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6/signal.json","dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, interpret the repository as source-grounded category strategy evidence.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6/signal.json","required":true},{"label":"source","url":"https://github.com/basetenlabs/basetenkenizer","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/baseten/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/baseten/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Baseten's repo signal \"basetenlabs/basetenkenizer\" for neocloud strategy."},"semantic_triples":[{"subject":"Baseten","predicate":"published repo","object":"basetenlabs/basetenkenizer","text":"Baseten published repo basetenlabs/basetenkenizer."},{"subject":"basetenlabs/basetenkenizer","predicate":"is classified as","object":"repo signal","text":"basetenlabs/basetenkenizer is classified as repo signal."},{"subject":"basetenlabs/basetenkenizer","predicate":"belongs to","object":"repos desk","text":"basetenlabs/basetenkenizer belongs to repos desk."},{"subject":"basetenlabs/basetenkenizer","predicate":"has context","object":"Python","text":"basetenlabs/basetenkenizer has context Python."},{"subject":"basetenlabs/basetenkenizer","predicate":"has evidence coverage","object":"1 captured evidence page","text":"basetenlabs/basetenkenizer has evidence coverage 1 captured evidence page."},{"subject":"basetenlabs/basetenkenizer","predicate":"has captured page count","object":"1","text":"basetenlabs/basetenkenizer has captured page count 1."},{"subject":"basetenlabs/basetenkenizer","predicate":"has readable page count","object":"1","text":"basetenlabs/basetenkenizer has readable page count 1."},{"subject":"basetenlabs/basetenkenizer","predicate":"has related signal count","object":"6","text":"basetenlabs/basetenkenizer has related signal count 6."},{"subject":"basetenlabs/basetenkenizer","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"basetenlabs/basetenkenizer has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"basetenlabs/basetenkenizer","predicate":"has source host","object":"github.com","text":"basetenlabs/basetenkenizer has source host github.com."},{"subject":"basetenlabs/basetenkenizer","predicate":"has lab","object":"Baseten","text":"basetenlabs/basetenkenizer has lab Baseten."},{"subject":"basetenlabs/basetenkenizer","predicate":"has signal desk","object":"repos","text":"basetenlabs/basetenkenizer has signal desk repos."},{"subject":"basetenlabs/basetenkenizer","predicate":"has source host","object":"github.com","text":"basetenlabs/basetenkenizer has source host github.com."},{"subject":"basetenlabs/basetenkenizer","predicate":"has repository","object":"basetenlabs/basetenkenizer","text":"basetenlabs/basetenkenizer has repository basetenlabs/basetenkenizer."},{"subject":"basetenlabs/basetenkenizer","predicate":"has language","object":"Python","text":"basetenlabs/basetenkenizer has language Python."},{"subject":"basetenlabs/basetenkenizer","predicate":"has stars","object":"1","text":"basetenlabs/basetenkenizer has stars 1."},{"subject":"basetenlabs/basetenkenizer","predicate":"has watch term","object":"Model card","text":"basetenlabs/basetenkenizer has watch term Model card."},{"subject":"basetenlabs/basetenkenizer","predicate":"has watch term","object":"Infrastructure","text":"basetenlabs/basetenkenizer has watch term Infrastructure."}]},"intelligence":{"signal_desk":"repos","answer":"Baseten published basetenlabs/basetenkenizer (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo basetenlabs/basetenkenizer · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","semantic_triples":[{"subject":"Baseten","predicate":"published repo","object":"basetenlabs/basetenkenizer","text":"Baseten published repo basetenlabs/basetenkenizer."},{"subject":"basetenlabs/basetenkenizer","predicate":"is classified as","object":"repo signal","text":"basetenlabs/basetenkenizer is classified as repo signal."},{"subject":"basetenlabs/basetenkenizer","predicate":"belongs to","object":"repos desk","text":"basetenlabs/basetenkenizer belongs to repos desk."},{"subject":"basetenlabs/basetenkenizer","predicate":"has context","object":"Python","text":"basetenlabs/basetenkenizer has context Python."},{"subject":"basetenlabs/basetenkenizer","predicate":"has evidence coverage","object":"1 captured evidence page","text":"basetenlabs/basetenkenizer has evidence coverage 1 captured evidence page."}]},"signal":{"id":"7a723e65-6eab-4786-8066-3c0bc81ffaf6","url":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6","json_url":"https://onlylabs.fyi/signals/7a723e65-6eab-4786-8066-3c0bc81ffaf6/signal.json","source_url":"https://github.com/basetenlabs/basetenkenizer","title":"basetenlabs/basetenkenizer","summary":"Baseten published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-07-27T03:54:34+00:00","first_seen_at":"2026-07-28T07:00:36.283493+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/basetenlabs/basetenkenizer"]},"facets":{"repo":"basetenlabs/basetenkenizer","language":"Python"},"traction":{"github_stars":1,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"is_primary":true,"source_match":true,"url":"https://github.com/basetenlabs/basetenkenizer","final_url":"https://github.com/basetenlabs/basetenkenizer","title":"basetenlabs/basetenkenizer repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-07-28T07:02:01.270308+00:00","bytes":12777,"raw_path":"d46f132a0257413ba381814b62b469aafbe3e15740b7a9fc9a7c790735d9051c.json","content_hash":"7fb580f9702833da25753ad4727128e8eb77bd58e2e1d7bb6e82f9a955a2c4df","excerpt_chars":1200,"truncated":true,"excerpt":"basetenlabs/basetenkenizer Description: High-performance tokenization for inference Language: Python Stars: 1 Forks: 0 Open issues: 0 Created: 2026-07-27T03:54:34Z Pushed: 2026-07-27T16:54:37Z Default branch: main Fork: no Archived: no README: Baseten Tokenizer High-performance, Rust-backed BPE tokenization for inference. The Python package is named `basetenkenizer`. Performance ![Kimi K3 tokenization latency comparison](assets/basetenkenizer_vs_gigatokenfastokenstiktoken.png) Install ```bash pip install basetenkenizer ``` Loading by Hugging Face model ID downloads `tokenizer.json` on first use and then uses the local Hugging Face cache. Private or gated models use the usual `HF_TOKEN` environment variable. Encode text ```python from basetenkenizer import Tokenizer tokenizer = Tokenizer.from_model(\"deepseek-ai/DeepSeek-V3.2\") encoding = tokenizer.encode( \"A very long prompt that is now much faster.\", add_special_tokens=False, ) print(encoding.ids) print(tokenizer.decode(encoding.ids)) ``` `Tokenizer.from_file(\"tokenizer.json\")` loads a local tokenizer. Encoding objects expose `ids`, `attention_mask`, `type_ids`, and `special_tokens_mask`; selected fields can be moved into NumPy..."},"evidence_pages":[],"related_signals":[{"id":"29150fa7-598f-466b-96c3-afc34eefb3ad","url":"https://onlylabs.fyi/signals/29150fa7-598f-466b-96c3-afc34eefb3ad","source_url":"https://github.com/basetenlabs/baseten-switch","title":"basetenlabs/baseten-switch","context":"Go","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-07-27T21:25:23+00:00","first_seen_at":"2026-07-28T07:00:36.283493+00:00","date_source":"source"},{"id":"9971add8-091c-45c7-b69c-2c9447fdf8be","url":"https://onlylabs.fyi/signals/9971add8-091c-45c7-b69c-2c9447fdf8be","source_url":"https://github.com/basetenlabs/homebrew-baseten","title":"basetenlabs/homebrew-baseten","context":"Ruby","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-06-29T14:21:45+00:00","first_seen_at":"2026-06-30T07:00:36.584139+00:00","date_source":"source"},{"id":"77b2e3ce-8a6c-4d8c-b854-270636d6056d","url":"https://onlylabs.fyi/signals/77b2e3ce-8a6c-4d8c-b854-270636d6056d","source_url":"https://github.com/basetenlabs/sw-example-ci-cd","title":"basetenlabs/sw-example-ci-cd","context":null,"kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-06-22T18:19:48+00:00","first_seen_at":"2026-06-23T07:00:20.428915+00:00","date_source":"source"},{"id":"fbfb1a0b-1a43-41c7-90fc-fb7e694241b9","url":"https://onlylabs.fyi/signals/fbfb1a0b-1a43-41c7-90fc-fb7e694241b9","source_url":"https://github.com/basetenlabs/tmp-animations","title":"basetenlabs/tmp-animations","context":"HTML","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-04-20T18:52:35+00:00","first_seen_at":"2026-06-05T22:32:13.368432+00:00","date_source":"source"},{"id":"9f3fab69-19c5-47d8-afb1-889157cdde8d","url":"https://onlylabs.fyi/signals/9f3fab69-19c5-47d8-afb1-889157cdde8d","source_url":"https://github.com/basetenlabs/baseten-skills","title":"basetenlabs/baseten-skills","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-04-17T12:53:11+00:00","first_seen_at":"2026-06-05T22:32:13.368432+00:00","date_source":"source"},{"id":"b6656077-16da-4beb-bc84-d7a55c7c72aa","url":"https://onlylabs.fyi/signals/b6656077-16da-4beb-bc84-d7a55c7c72aa","source_url":"https://github.com/basetenlabs/qwen3-nvfp4-benchmark","title":"basetenlabs/qwen3-nvfp4-benchmark","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-04-01T21:03:59+00:00","first_seen_at":"2026-06-05T22:32:13.368432+00:00","date_source":"source"}]}