litellm/litellm-rust
mateo-berri 99eded71e8 fix(gateway): apply a deployment's sampling params on /v1/messages
The gateway ignored temperature, top_p, top_k, max_tokens, and
stop_sequences set in a deployment's litellm_params, while the Python
proxy sends them upstream. Merge them under the client body, so a value
the client sets, null included, still wins.
2026-10-30 02:10:52 -07:00
..
.agents/skills feat(skills): add a litellm-setup agent skill (#47731) 2026-10-28 15:44:43 -07:00
crates fix(gateway): apply a deployment's sampling params on /v1/messages 2026-10-30 02:10:52 -07:00
docs/adrs docs(rust): add ADRs for the Rust core (#45205) 2026-10-08 10:21:56 -07:00
.gitignore feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033) 2026-06-23 13:16:47 -07:00
AGENTS.md refactor(rust): adopt one error discipline across litellm-rust with source chains and Report (#48042) 2026-10-28 09:22:11 -07:00
Cargo.lock build(model-catalog): ship the cost map inside the native extension (#48907) 2026-10-29 07:55:02 -07:00
Cargo.toml refactor(model-catalog): parse, lower and validate the catalog into typed prices (#48853) 2026-10-28 18:24:40 -07:00
clippy.toml build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039) 2026-10-28 07:32:40 -07:00