Commit Graph
165 Commits
Author SHA1 Message Date
3962042304 [Bugfix][V1][Multimodal] Recover from P0/P1 processor cache drift (#46747) (#46747)
Signed-off-by: William Zhao <williamzh@meta.com>
Signed-off-by: WillZZZy <93454470+WillZZZy@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Claude <noreply@anthropic.com>
2026-08-12 12:06:57 +08:00
Clinton ThomasLucas Bourtoulemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
b64a2708b0 Bound generation inputs before expensive work (#51447)
Signed-off-by: Clinton Thomas <1033162+KernelClint@users.noreply.github.com>
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-11 22:03:50 +08:00
aoshen02Claude Opus 4.6mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
33584901ba [Frontend] Add content_parts to /inference/v1/generate for raw multim… (#51478)
Signed-off-by: Allen Shen <aoshen@inferact.ai>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-11 10:00:12 +08:00
Bugen Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> f1e921b6d6 [Rust Frontend] Support dynamic tools from developer messages (#51144)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-10 18:30:38 -07:00
Bugen Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> d8c70f2243 [Rust Frontend] Upgrade MiniJinja to 2.22 & remove method lookup workaround (#51235)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-11 00:23:24 +00:00
Connor Carpenterandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> fa722b9f01 [Rust Frontend][gRPC] Add explicit data-parallel rank routing (#51178)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-10 15:05:24 -07:00
Sage 865781e627 [Rust Frontend] Add standalone Rust renderer (#50289) 2026-08-06 11:23:26 +00:00
Chauncey 22170354d8 [Feature] Parse request priority from HTTP header (#51089)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-08-05 21:10:29 -07:00
SageandBugen Zhao 5bf32605a9 [Rust Frontend] Deduplicate request preprocessing for /tokenize (#50448)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-08-05 08:27:35 +00:00
Bugen Zhao 7743486190 [Frontend] DeepSeek V4 0731 reasoning effort prompts & mappings (#50580) 2026-08-04 08:51:32 -07:00
Connor CarpenterandBugen Zhao e98a8774cb [Rust Frontend][gRPC] Add multimodal image inference (#50368)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-08-04 09:34:31 +00:00
Bugen Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 0b1c151cbc [Rust Frontend] Align tool rendering for Kimi K3 (#50540)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-08-04 08:03:46 +00:00
Reid 72cd5424da [Rust][Benchmark] Preserve UTF-8 across benchmark stream chunks (#50868)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-08-04 06:15:02 +00:00
Karen Chung f57123aa2d feat(frontend): session id plumbing into requests (#48048)
Signed-off-by: Karen Chung <karenc@nvidia.com>
2026-08-03 22:18:58 +00:00
zcxGGmuandzq c4e9f09de7 [Bugfix][Frontend] Reject empty gRPC stop strings (#50746)
Signed-off-by: zq <zhouquan1511@163.com>
Co-authored-by: zq <zhouquan1511@163.com>
2026-08-03 20:50:15 +00:00
Reid 62195e9784 [Rust][Benchmark] Prevent invalid token IDs in random benchmarks (#50058)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-08-01 03:20:29 +00:00
Bugen Zhao ab98034d4c [Frontend][Bugfix] Use default tool call IDs for Kimi K3 for conversation-level uniqueness (#50420)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-31 10:02:17 +08:00
Samuel LaferriereandClaude d6938b7408 [Bugfix][Rust Frontend] Select earliest-completing stop string (#50200)
Signed-off-by: Samuel Laferriere <9342524+samlaf@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-07-31 00:33:19 +00:00
Bugen ZhaoandOpenAI Codex e9096fcb12 [Rust Frontend] Improve startup failure and readiness logs (#50406)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-30 14:18:17 -07:00
Bugen Zhao 629a938a92 [Frontend] Preserve bare Inkling text in Python and Rust parsers (#50403)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-30 12:25:10 -07:00
Connor CarpenterandNick Hill 48fc2e2797 feat(grpc): add KV event source discovery (#50033)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-07-29 13:46:40 -07:00
ReidandBugen Zhao 242c591d5a [Rust Frontend] Send multimodal tensors in auxiliary frames (#49341)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-29 12:21:09 +00:00
Maria Guevara c44e191b01 [Rust Frontend] Add --limit-mm-per-prompt support (#49604)
Signed-off-by: Maria Guevara <kawaiiplush14@gmail.com>
2026-07-29 17:21:41 +08:00
Bugen Zhao 2899dca843 [Model] Add Kimi K3 support: Rust frontend [1/2] (#50104)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-28 14:31:13 -07:00
Bugen Zhao d552a68645 [Rust Frontend] Extract shared tracing setup logic into vllm-tracing (#50129)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-28 19:31:15 +00:00
Reid 912d6b619d [Rust Frontend] Align sampling validation with Python (#47494)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-07-28 12:02:00 +00:00
Reid bf9f23003c [Rust Frontend] Fix finish reason for named tool choices (#49496)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-07-28 10:53:18 +00:00
Bugen ZhaoandOpenAI Codex 5ed3faa43d [Rust Frontend] Add ordinary-text tokenizer encoding (#49992)
Co-authored-by: OpenAI Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-28 15:46:51 +08:00
Connor CarpenterandNick Hill e3c2fc3b3c [Rust Frontend][gRPC] Add server and model discovery (#49491)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-07-27 09:53:27 -07:00
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 59a6b0411d [Core] Fix internal LB load-balancing (#49204)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-27 14:00:46 +00:00
Bugen ZhaoandOpenAI Codex 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
Sage 0f6cf7f628 [Rust Frontend] Extract request preparation from the inference path (#49045)
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2026-07-22 11:31:36 +00:00
Connor CarpenterandOpenAI Codex c79ad3ae21 [Rust Frontend][gRPC] Add abort control RPC (#49255)
Co-authored-by: OpenAI Codex <codex@openai.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
2026-07-22 11:31:01 +00:00
Bugen Zhao eb44b3aaa4 [Rust][Benchmark] Use async HTTP clients (#49295)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-21 16:53:57 +08:00
Bugen Zhao 8688a06d67 [Rust][Benchmark] Use tracing for logs (#48937)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-21 05:18:13 +00:00
Salt Satoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> f25953cc59 [Bugfix][Rust Frontend] Handle zero-column logprobs payloads without panicking (#49113)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Feathbow <feathbow@gmail.com>
2026-07-21 04:30:29 +00:00
Connor Carpenterandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 1940c8441e [Rust Frontend][gRPC] Add engine-aware health reporting (#48992)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
2026-07-21 10:54:39 +08:00
Bugen Zhao e2d7adeb64 [Rust Frontend] Bump xgrammar-structural-tag and enable local extension (#49161)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-20 16:22:24 +01:00
Salt Sato d835ad572c [Bugfix][Rust Frontend] Map missing prompt logprobs for single-token prompts in chat and raw generate (#49111)
Signed-off-by: Feathbow <feathbow@gmail.com>
2026-07-20 10:00:06 +00:00
Reid 818cf61e91 [Rust Frontend] Fix macro-based content format detection (#49042)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-07-20 09:39:13 +00:00
Bugen Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> c01618fdc8 [Rust][Benchmark] Integrate vllm-bench to vllm-rs & vllm CLI (#48930)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-20 09:31:25 +00:00
Sageandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> f1f1259692 [Rust Frontend] Use zero-copy slicing for multimodal tensors (#48781)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2026-07-20 16:28:25 +08:00
yzong-rh a287eb163f [Front-end] [Messages] Populate num_cache_creation_tokens (#48535)
Signed-off-by: Yifan Zong <yzong@redhat.com>
2026-07-18 13:04:35 -04:00
Roy WangandBugen Zhao 9354f22204 [Rust][Benchmark] Port in vllm-bench (#48107)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: esmeetu <jasonailu87@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-17 14:25:29 +08:00
Reid 8c3393f373 [Bugfix][Rust Frontend] Limit chat top_logprobs in responses (#48134)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-07-16 09:41:44 +00:00
Chao-Ju Chenandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> ea1d65fe6d [Rust Frontend] Add Seed-OSS tool parser (#47741)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com>
2026-07-16 17:28:02 +08:00
ReidandBugen Zhao f44f3d6f79 [Rust Frontend] Wait for mock engine endpoints before ZMQ connect (#47965)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-07-16 09:20:31 +00:00
JinYan SuandBugen Zhao cc706b05a5 [Bugfix][Rust Frontend] Detokenizer: avoid leaking prompt on zero-generated-token completions (#47707)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: xiaguan <751080330@qq.com>
2026-07-16 09:11:21 +00:00
Reid dc9f845ddc [Rust Frontend] Fix mock engine test shutdown race (#48738)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2026-07-16 07:27:43 +00:00
6570c9800c [Model] Add Inkling model support [1/N] (#48799)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-15 23:40:07 -07:00