055f150df5
[Perf][Rust Frontend] Make histogram observations lock-free ( #58574 )
...
Co-authored-by: jthomson04 <jwillthomson19@gmail.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-25 10:25:10 +08:00
Harry Mellor and Claude Opus 5.5
d636456b1f
[Frontend] Remove the slow tokenizer mode ( #58545 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-09-24 08:48:28 -07:00
e430f7421f
[Bugfix][Rust Frontend] Prevent MM timing from enabling debug tracing ( #58378 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Signed-off-by: reidliu41 <reid201711@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-24 09:22:23 +00:00
e028554a1f
[Rust Frontend] Support --sse-keep-alive-interval ( #58306 )
...
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-24 06:19:14 +00:00
Biswa Panda and Codex
cf78797cb7
[Rust Frontend] Pass vision preprocessing context for Nemotron-H ( #57634 )
...
Pass the remaining engine context-length budget to model-owned vision processors through VisionPreprocessingContext. Preserve Nemotron batched engine fields and recognize llm_config as a text_config alias.
Use the merged upstream llm-multimodal revision f0985ef65967615db2c79279aa07818499301bfd.
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-24 14:08:26 +08:00
Bugen Zhao and Claude Opus 5.5
a1b6763df6
[Rust Frontend] Accept custom chat roles for HF templates ( #58311 )
...
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-24 13:43:34 +08:00
Bugen Zhao and Claude Opus 5.5
a5603f21ae
[Rust Frontend] Recognize new frontend-owned serve args as unsupported or no-op ( #58330 )
...
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-24 13:43:24 +08:00
Bugen Zhao and Codex
81d7293c21
[Rust Frontend] Construct model-owned vision processors through specs ( #58109 )
...
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-22 10:01:53 +00:00
Bugen Zhao
a6c47fbbf4
[Rust Frontend] Separate multimodal instrumentation from request timing ( #58084 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-22 06:57:56 +00:00
Bugen Zhao and Codex
496c6472cb
[Rust Frontend] Build full-output grammars from initialized reasoning parsers ( #57340 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
2026-09-22 06:11:55 +00:00
Bugen Zhao and Claude Fable 5.1
d50723df04
[Rust Frontend] Introduce parser-owned output grammar interfaces ( #55269 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
2026-09-22 05:35:07 +00:00
f84325c48c
[Frontend][Rust] Add mm-processor benchmark for Rust frontend ( #51922 )
...
Signed-off-by: Karthik Gangula <gangula-karthik@users.noreply.github.com >
Signed-off-by: gangula-karthik <gkarthik923@gmail.com >
Signed-off-by: Isotr0py <Isotr0py@outlook.com >
Co-authored-by: Karthik Gangula <gangula-karthik@users.noreply.github.com >
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com >
2026-09-22 05:08:35 +00:00
Bugen Zhao and Codex
ff3c9cba3f
[Rust Frontend] Add MiMo V2.5 parser support ( #57933 )
...
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-22 04:27:09 +00:00
Karen Chung
986e217158
[Feature] Add first-class KV hints request envelope for programmatic KV management ( #53423 )
...
Signed-off-by: Karen Chung <karenc@nvidia.com >
2026-09-21 09:56:11 -07:00
10e6a7f210
[Frontend] Expose per-request spec decode metrics in generate API ( #43310 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: Codex <codex@openai.com >
2026-09-20 12:21:33 +00:00
90531daf6d
[Core][Frontend] Bind KV-event publishers at port 0 and expose the bound endpoints ( #55844 )
...
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com >
Co-authored-by: mukeshbhandarkar <shell00035@gmail.com >
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com >
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
Co-authored-by: aoshen02 <aoshen@inferact.ai >
2026-09-18 18:11:05 -07:00
c58532c86b
[Frontend] Upgrade XGrammar to 0.2.7 and Rust structural tags to 0.3.0 ( #57272 )
...
Co-authored-by: Codex <noreply@openai.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-18 11:44:05 +00:00
Biswa Panda and Bugen Zhao
95d723700b
[Rust Frontend] Return sampling masks over gRPC ( #56777 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: Biswa Panda <biswa.panda@gmail.com >
2026-09-18 08:26:17 +00:00
39e33db7f3
[Frontend] Fix the parsing of missing string= in DeepSeek V4 ( #56271 )
...
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: lazymio <mio@lazym.io >
2026-09-18 05:11:24 +00:00
dee37d8911
[Frontend] Add --tool-strict-level for server-side control for structural tag activation ( #56268 )
...
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: lazymio <mio@lazym.io >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-18 04:32:39 +00:00
092bdd6d57
[Frontend][Core] Add release_kv_cache_memory() API ( #44890 )
...
Signed-off-by: Dakai An <dakaian108@gmail.com >
Signed-off-by: AlanFokCo <alanfok2868@gmail.com >
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Signed-off-by: Dakai An <77474977+andakai@users.noreply.github.com >
Co-authored-by: AlanFokCo <alanfok2868@gmail.com >
Co-authored-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-09-18 07:12:12 +08:00
aoshen02
b978df3299
Revert "[Frontend] Omit absent fields from /inference/v1/generate stream chunks" ( #57302 )
2026-09-16 23:31:59 -07:00
aoshen02 and Claude Fable 5.1
8538017f4b
[Frontend] Omit absent fields from /inference/v1/generate stream chunks ( #57264 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
2026-09-17 05:58:56 +00:00
Alec and Codex
28ec03bc6e
[Bugfix][Rust Frontend] Accept appended EngineCoreOutput fields ( #56533 )
...
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Alec Flowers <aflowers@nvidia.com >
2026-09-17 01:54:43 +00:00
Bugen Zhao
e52da038d1
[Rust Frontend] Normalize native renderer reasoning controls ( #56998 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-16 18:15:05 -07:00
aoshen02
0983aef8da
[Frontend] Return prompt metadata from /inference/v1/generate ( #53187 )
2026-09-16 15:29:07 -07:00
Alec and Codex
9639cbde04
[Rust Frontend] Expose local DP size in gRPC Control metadata ( #57116 )
...
Signed-off-by: Alec Flowers <aflowers@nvidia.com >
Co-authored-by: Codex <noreply@openai.com >
2026-09-16 11:28:08 -07:00
f37c550bf6
[Feature][Frontend] Expose effective attention block size for DCP ( #56538 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
Signed-off-by: Julien Darve <jdarve@NVIDIA.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-16 08:29:43 +00:00
Islam and Bugen Zhao
c16bb6068f
[Bugfix][Rust Frontend] Tolerate NaN-corrupted logprobs in engine-core ( #51026 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: Islam <islam.almersawi@openinnovation.ai >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-16 03:10:58 +00:00
Bugen Zhao
bfd713bf8b
[Rust Frontend] Support HF config overrides --hf-overrides ( #56931 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-16 02:52:55 +00:00
Reid and Bugen Zhao
0673de9800
[Rust Frontend][Metrics] Add per-request preemption histogram ( #57033 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: reidliu41 <reid201711@gmail.com >
2026-09-16 02:51:17 +00:00
Bugen Zhao and Codex
78eaaad2c7
[Rust Frontend] Add iteration token histogram ( #56990 )
...
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-15 12:12:15 +00:00
Yeonwoo Sung and Bugen Zhao
142020c6c2
[Bugfix][Rust Frontend] Honor add_generation_prompt in DeepSeek V3.2/V4/V4.1 renderers ( #56593 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: YeonwooSung <neos960518@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-15 10:03:26 +00:00
Kevin H. Luu and OpenAI Codex
772e4f05fa
[Bugfix][Rust] Fix HF multi-turn dataset integration ( #56915 )
...
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-09-14 18:04:46 -07:00
f0a61bd438
[Rust][Benchmark] Support HF ShareGPT datasets in multi-turn mode ( #51104 )
...
Signed-off-by: xiaguan <751080330@qq.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-14 16:48:23 -07:00
Kevin H. Luu and Sherlock
d320a21431
[Bugfix][Rust Frontend] Restore prost test dependency ( #56866 )
...
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com >
Co-authored-by: Sherlock <sherlock@raft.ai >
2026-09-14 14:37:44 -07:00
Nicolò Lucchesi and Codex
1713a09491
[Rust Frontend] Forward per-request watermarking controls ( #56338 )
...
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai >
2026-09-14 23:17:02 +08:00
7b1ea3f524
[Bugfix][Rust Frontend][Multimodal] Align DeepSeek V4.1 and Kimi K3 media with rendered placeholders ( #56366 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: reidliu41 <reid201711@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-14 10:37:59 +00:00
Martin Hickey
934b1fcbcb
[Frontend] Replace VLLM_ENABLE_SCALE_OUT_ENDPOINTS with --enable-scale-out ( #55176 )
...
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com >
2026-09-14 10:02:14 +00:00
Alec and OpenAI Codex
e6b4e47d2d
[Bugfix][Rust Frontend] Preserve selected-token logprob mode ( #56406 )
...
Co-authored-by: OpenAI Codex <noreply@openai.com >
Signed-off-by: Alec Flowers <aflowers@nvidia.com >
2026-09-14 07:05:33 +00:00
7632f767f0
[Rust Frontend] Support HTTP RL weight synchronization ( #56567 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: Wang Zupeng <zupenwang@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-14 03:37:04 +00:00
Clinton Thomas and Lucas Bourtoule
22f6e4eccb
[Frontend][Rust] Reject empty structured-output values ( #54821 )
...
Signed-off-by: Clinton Thomas <1033162+KernelClint@users.noreply.github.com >
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com >
2026-09-12 19:12:25 +04:00
Bugen Zhao
eed1f3d0c6
[Rust Frontend] Support generation blocks in HF chat template ( #56378 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-12 04:56:55 +00:00
Bugen Zhao and Codex
485421b1c3
[Rust Frontend] Honor HF revisions, offline mode, and cache directory ( #56386 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
2026-09-12 03:39:17 +00:00
31759ccb6d
[Rust Frontend][Multimodal] Accept preprocessed multimodal gRPC features ( #55047 )
...
Signed-off-by: Biswa Panda <biswa.panda@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
2026-09-12 02:29:49 +00:00
Alec and Codex
988d9b6777
[Rust Frontend][gRPC] Surface engine generation errors ( #56405 )
...
Signed-off-by: Alec Flowers <aflowers@nvidia.com >
Co-authored-by: Codex <noreply@openai.com >
2026-09-11 15:31:55 -07:00
79c137c6ad
[Bugfix][Rust Frontend][Renderer] Align DeepSeek tool-call arguments with deepseek-recipe ( #56260 )
...
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Codex <noreply@openai.com >
Signed-off-by: JinYan Su <751080330@qq.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-11 10:19:55 +00:00
69db1c26b4
[CI/Build][Rust Frontend] Publish vllm-proto on crates.io ( #56365 )
...
Co-authored-by: OpenAI Codex <noreply@openai.com >
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Julien Darve <jdarve@NVIDIA.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-11 16:28:52 +08:00
Bugen Zhao and Isotr0py
b47b01cf33
[Model][Frontend] Support DeepSeek-V4.1-Flash in Rust and Python frontends ( #56208 )
...
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: Isotr0py <Isotr0py@outlook.com >
2026-09-10 01:15:06 -07:00
3735c2d5f5
[Security][Rust Frontend] Normalize HTTP method labels in metrics ( #56058 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-09-10 10:54:40 +08:00