pullrequests Search Results · bucket language:JavaScript language:JavaScript language:Python language:Python language:JavaScript
Filter by
897k results
Summary
- extend the shared prefill CUDA Graph ladder with 1- and 2-token buckets
- centralize effective capture-cap and bucket resolution across model defaults and operator overrides ...
Summary
Items 9–14 of the Python hardening plan. This branch includes #30–#37 (bucket 1) as merges. Merge those first and this
PR s diff shrinks to the six bucket-2 commits; merging this PR alone ...
... release.
The only changes are the image and the start command (the binary is now called silo). The service name, volume,
MINIO_ROOT_* variables, healthcheck endpoint and bucket-creation commands are ...
... .*, which SGLang remaps only after each bucket arrives. Miles therefore split wq_a + wkv or
compressor.wkv + wgate across update calls, and SGLang asserted on a half-filled fusion cache.
Validation ...
... -admins see a view-only
note. Media is stored publicly — anyone with the link can open them.
- Lists, uploads, and deletes go directly through Supabase Storage on the gallery bucket ...
... by RLS, unlike generated S3
project keys (unrestricted across all buckets, bypass RLS). The guide requires a legacy anon key, project reference and
real user JWT; sb_publishable_ is not supported in ...
Refactored iter_resolved to prevent O(N × M) N+1 query degradation by batching database reads and writes grouped by hash
index buckets. It caches existing bucket matches in bounded in-memory O(1 ...
blocked:draft
... durations and Anthropic RFC 3339 reset values, then delays
the next request when a matching request bucket has at most two requests remaining.
The captured state is in-memory and is accepted only when ...
area/config
comp/agent
P3
type/feature