waffles/consciousness
1
0
Fork 0
forked from kent/consciousness
Code Pull requests Activity

agent: bump tonic gRPC message caps to 64 MiB

Browse source 
The default 4 MiB cap on encoded/decoded messages is too small for
the multimodal Generate path: Qwen3.6-VL high-res patches put 5–8 MiB
of pre-encoded image bytes inline in a single Generate request, and
Done events carrying full per-token readout vectors can also exceed
4 MiB on long runs. Hit "ResourceExhausted: Received message larger
than max (5799108 vs. 4194304)" from the salience server.

Bump both encode and decode caps on every cloned SalienceClient. The
matching server-side bump is in vllm/entrypoints/salience/server.py.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-04-24 22:36:10 -04:00
commit 10c8878f1c
1 changed files with 10 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/agent/api/mod.rs
View file

@ -117,6 +117,12 @@ impl ApiClient {
/// the channel on first call and reuses it thereafter across /// the channel on first call and reuses it thereafter across
/// every ApiClient clone. All scoring / inference / session /// every ApiClient clone. All scoring / inference / session
/// RPCs flow through this single multiplexed HTTP/2 connection. /// RPCs flow through this single multiplexed HTTP/2 connection.
///
/// Bumps tonic's default 4 MiB encode/decode caps to 64 MiB on
/// every client. Multimodal Generate requests carry pre-encoded
/// image bytes inline (Qwen3.6's 768×768 patches at high res
/// land around 5–8 MiB per turn), and Done events with full
/// per-token readout vectors can also exceed 4 MiB on long runs.
pub async fn salience_client(&self) -> Result< pub async fn salience_client(&self) -> Result<
salience::pb::salience_client::SalienceClient<tonic::transport::Channel> salience::pb::salience_client::SalienceClient<tonic::transport::Channel>
> { > {
@ -127,7 +133,10 @@ impl ApiClient {
self.base_url, grpc_url); self.base_url, grpc_url);
salience::connect_channel(&grpc_url).await salience::connect_channel(&grpc_url).await
}).await?; }).await?;
Ok(salience::pb::salience_client::SalienceClient::new(ch.clone())) const MAX_GRPC_MESSAGE_BYTES: usize = 64 * 1024 * 1024;
Ok(salience::pb::salience_client::SalienceClient::new(ch.clone())
.max_decoding_message_size(MAX_GRPC_MESSAGE_BYTES)
.max_encoding_message_size(MAX_GRPC_MESSAGE_BYTES))
} }
/// Stream generation via a gRPC session. Walks the prompt chunks /// Stream generation via a gRPC session. Walks the prompt chunks