3 people fd9d2ede6f [Rust Frontend] Keep --max-model-len engine-owned (#49944) ...

Co-authored-by: OpenAI Codex <codex@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>

2026-07-27 14:50:08 +08:00

..

bench

[Rust][Benchmark] Use async HTTP clients (#49295)

2026-07-21 16:53:57 +08:00

chat

[Rust Frontend] Extract request preparation from the inference path (#49045)

2026-07-22 11:31:36 +00:00

cmd

[Rust Frontend] Keep --max-model-len engine-owned (#49944)

2026-07-27 14:50:08 +08:00

engine-core-client

[Bugfix][Rust Frontend] Handle zero-column logprobs payloads without panicking (#49113)

2026-07-21 04:30:29 +00:00

llm

[Front-end] [Messages] Populate num_cache_creation_tokens (#48535)

2026-07-18 13:04:35 -04:00

managed-engine

[Rust Frontend] Keep --max-model-len engine-owned (#49944)

2026-07-27 14:50:08 +08:00

metrics

[CI] Add SPDX license header to Rust/Protobuf sources (#48472)

2026-07-13 10:22:47 +01:00

mock-engine

[Rust Frontend] Fix mock engine test shutdown race (#48738)

2026-07-16 07:27:43 +00:00

parser

[Rust Frontend] Bump xgrammar-structural-tag and enable local extension (#49161)

2026-07-20 16:22:24 +01:00

server

[Rust Frontend][gRPC] Add abort control RPC (#49255)

2026-07-22 11:31:01 +00:00

text

[Rust Frontend] Extract request preparation from the inference path (#49045)

2026-07-22 11:31:36 +00:00

tokenizer

[Bugfix][Rust Frontend] Detokenizer: avoid leaking prompt on zero-generated-token completions (#47707)

2026-07-16 09:11:21 +00:00