pullrequests Search Results · bucket language:JavaScript language:Java language:Python language:JavaScript language:JavaScript
Filter by
1M results
Overview
When _get_kv_cache_groups_uniform_page_size groups KV cache specs by (is_draft, type_id, page_size_bytes), it previously
computed min_num_layers across all buckets—including draft-only ...
bug
kv-cache-manager
arashb
Summary
Writes to Rapid Cache Ultra (RCU) buckets now go through the gRPC appendable writer (AsyncAppendableObjectWriter) that
zonal buckets already use, with storage_class= RAPID . An RCU bucket ...
yuxin00j
Bug
Performance
SQL
tandem
kafka1991
pattch-openclaw
Bomjans3_bucket_exists converts every S3 error code to an integer. Named codes such as NoSuchBucket and AccessDenied therefore
raise ValueError, interrupting the bucket check used by aws configservice ...
Shubham-Padkonde
🚨 Severity: HIGH
💡 Vulnerability: get_user_id used get_unverified_claims to extract the user ID for rate limiting, allowing an attacker
to spoof tokens and poison other users rate limit buckets ...
Akullganesh19
...
- minio_s3_bucket_replication no longer pairs a rule with the remote target of the rule that used to sit at the same
position (# #8203;1250). Removing a rule that is not the last one used to send ...
renovate[bot]
Motivation
get_batch_sizes_to_capture drops the top decode bucket when --cuda-graph-max-bs is below the request pool and not a
multiple of the attention-TP alignment. Example: DP attention with attn ...
blackwell
lora
Denji-kk
...
How it solves it:
- The window and pools are keyed by provider bucket: the organization of the deployment that serves the call plus its
model class
- Admission moves to the router stage that ...
sjawhar-agent[bot]