34 Commits
Author SHA1 Message Date
MOVZXandHinata 61fbe0b865 [Mini-VLLM] Remove unreferenced definitions found by static scan
A symbol scan over every tracked file found 123 top-level definitions in
vllm/ with zero references, including references inside strings. All of
them came from features this fork deleted earlier.

- Delete dead attention helpers: MLADCPManager, split_prefill_chunks, the
  reshape helpers, compute_varlen_chunk_metadata, the LINEAR backend's
  unused BailingLinearAttentionBackend, and the sparse flash-attn entry
  points.
- Delete the CPU and AMX op wrappers from _custom_ops.py: cpu_mla_decode,
  cpu_mla_extend, cpu_mla_get_scheduler_metadata,
  gather_mla_context_cache_cpu.
- Delete dead quantization helpers: awq_pack, gptq_pack,
  gptq_quantize_weights, get_and_maybe_dequant_weights,
  marlin_quant_fp8_torch, the rand_marlin_weight_*_like pair,
  ocp_mx_weight_dtype_and_rows, get_fp8_block_weight_scale,
  input_to_float8.
- Delete dead model helpers: resolve_visual_encoder_outputs,
  run_dp_sharded_vision_model, fast_topk, get_layer_index,
  is_pp_missing_parameter, skip_spec_layers, KimiK3MergedQKVGateLinear,
  selective_scan_fn, causal_conv1d_update_torch.
- Delete dead utils: format_kib, format_mib, chunk_list, prev_power_of_2,
  split_host_port, join_host_port, make_zmq_path, make_async_with_semaphore,
  is_meta_module, is_non_overlapping_and_dense, supports_xpu_graph,
  create_kv_caches_with_random*, and the unused has_* capability probes.
- Delete the unreachable deep-gemm mega-MoE warmup path, which imported
  vllm.models.deepseek_v4.nvidia.model and vllm.models.kimi_k3.nvidia.model,
  neither of which exists anymore.
- Drop the imports and the two now-empty guards left behind.

Verified statically: every changed file compiles, no unused import
remains, and no deleted name is referenced in vllm, tests or csrc. The
runtime gates still need the Python environment rebuilt.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 21:39:56 +07:00
MOVZXandHinata 5aa2ac64f8 [Mini-VLLM] Remove LoRA, plugins, speech-to-text and scale-out surfaces
Production runs one static model behind the OpenAI-compatible API. Every
adapter path and non-OpenAI HTTP surface is unreachable there.

- Delete the LoRA stack: vllm/lora, LoRARequest on the engine wire, the
  scheduler, worker, cudagraph and MoE plumbing, LoRA metrics, the lora
  CLI group, and the LoRA tests.
- Drop the plugin loader in vllm/plugins. Platform resolution is now
  CUDA-only and the general/stat-logger plugin hooks are gone.
- Delete the speech-to-text and realtime entrypoints, the scale-out
  render routes, and vllm/config/speech_to_text.py. GenerationTask is
  generate-only.
- Cut DecodeBenchConnector and the disagg-prefill doc and image. The
  Multi, Offloading and Example connectors stay; production uses the
  CPU KV offload tier.
- Delete the ROCm-only fused KDA chunk kernel (2346 lines) with its CMake
  arch gate, declarations and op registrations. The CUDA build never
  defined the guard and no Python caller existed.
- Delete the orphan Mistral and Pixtral chat fixtures and examples/.
- Fix _check_model: removing the LoRA early return made every request
  fail with "The model ... does not exist. Valid aliases: ...".

Verified on an RTX 3090: import sweep reports 1242 modules with 7 known
optional-dependency failures; a live server answers chat, completions,
responses, tokenize and detokenize with zero log errors and 404 for the
removed surfaces; collection yields 8558 tests with the 3 pre-existing
errors; ruff adds no new finding; the incremental _C build succeeds.

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 21:06:19 +07:00
MOVZXandHinata e61dcb9143 [Mini-vLLM] SM86-only cut: models, backends, Rust, tests
- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries
- Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels
- Remove inc/quark quant loaders; keep compressed-tensors and Marlin
- Drop the Rust frontend, pooling entrypoints, and idle test suites
- Rebuild kernels for sm_80;sm_86 and strip the extensions
- Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-18 19:19:56 +07:00
Talor Abramovich 81e42c9987 [Feature][Frontend] Control the log level of request JSON body using env var (#60630)
Signed-off-by: talora <talora@nvidia.com>
2026-10-15 11:07:19 +00:00
Flora FengandChauncey 80dd705c1d [Frontend] Make finish_reason and Responses item status truthful (#59324)
Signed-off-by: Flora Feng <4florafeng@gmail.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-10-15 10:12:02 +01:00
GuanLuoandsfeng33 6d1daa9fe5 [Bugfix][Frontend] Expose completion response schemas in OpenAPI (#60926)
Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
2026-10-13 18:54:06 +00:00
SrirajandFlora Feng db6e3cd8c4 [Bugfix][Frontend] Log the full request body when max_log_len is unset (#60310)
Signed-off-by: sricursion <sricursion@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
2026-10-07 00:42:17 +00:00
Flora Feng 797505747f [Bugfix][Frontend] Honor parallel_tool_calls=false in the Responses API (#59298)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-09-29 22:36:11 +00:00
Mark McLoughlinandAI Assistant 45d56c0baf [Core] Model console logging as CLI configuration (#57205)
Add `--logging-config` CLI argument which can be supplied as
JSON or using dotted arguments. The `--log-level` argument
is provided for convenience, and `--log-config-file` is deprecated
in favor of `--logging-config.pylogging_config_file`.

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: AI Assistant <noreply@openai.com>
2026-09-25 11:36:59 +01:00
Talor Abramovich 28282ffe34 [Feature][Frontend] Request JSON body debug logging on --enable-log-requests flag (#58163)
Signed-off-by: talora <talora@nvidia.com>
2026-09-24 08:08:40 +00:00
Harry MellorandClaude Opus 5 651a88c09a [CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 10:57:24 -07:00
Harry MellorandClaude Opus 5 8c1557a79c Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 16:44:29 +00:00
wang.yuqi fe4d4109c2 [Frontend][last/N] Move all non-OpenAI content out of the OpenAI folder. (#56369)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-09-11 05:33:26 +00:00
Raphaël RiallandOpenAI Codexmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
ea40bb9e90 [feature] Watermarked generation and detection (Gumbel-max algorithm) (#54053)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-09 21:00:15 -07:00
wang.yuqiandCyrus Leung eeb549a74d [Frontend] Move engine/protocol.py out openai folder (#54492)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2026-08-31 10:13:50 +00:00
Moe Huzaifa 3e833933dc [Bugfix][Frontend] Keep credentials out of the Rust frontend launch log (#53738)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
2026-08-25 16:32:12 +00:00
wang.yuqi 735daf8ef6 [Frontend] Move cli_args.py and dp_supervisor.py out openai folder (#53659)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-08-25 07:02:32 +00:00
Moe Huzaifa d3e2888c75 [Bugfix][Frontend] Redact hf_token in the non-default args log (#53625)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
2026-08-25 03:06:46 +00:00
wang.yuqi eac636a7fa [Frontend] Move api_server.py out openai folder (#52131)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-08-19 09:43:46 +00:00
LuckyStep 9a9aa2b017 [Bugfix] Redact api_key in non-default args log (#52523)
Signed-off-by: LuckyStep <67696304+Andy365-365@users.noreply.github.com>
2026-08-19 15:52:53 +08:00
wang.yuqi 93550cc4cd [Frontend] Consolidate entrypoint middleware (#52309)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-08-17 06:17:15 +00:00
wang.yuqi b8165e5e58 [Frontend] Consolidate entrypoint exception handler (#52261)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-08-14 09:27:24 +00:00
yang rui 152c913a63 [Frontend] Log output token IDs at DEBUG level (#52098)
Signed-off-by: ruirui6946 <142162413+ruirui6946@users.noreply.github.com>
2026-08-13 13:11:51 +00:00
andrewbcohereandCyrus Leung 9c110fa522 [Frontend] Cohere chat v2 api support (#47189)
Signed-off-by: Andrew Berneshawi <andrewberneshawi@cohere.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-07-31 22:53:54 -07:00
Zach Zhu 58f9659397 [Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)
Signed-off-by: Zach Zhu <zzqshu@126.com>
2026-07-29 04:20:40 +00:00
Nick Hill 4809de7317 [Misc] Fix terminal output logo coloring (#49344)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-07-22 00:21:29 +00:00
Ning Xie b7c20d0cfa [chore] adjust logo be more friendly to white background terminal (#48938)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2026-07-20 15:15:28 -07:00
Muhammad FawazandMahad Durrani e87521626f Sanitize server file paths from validation error responses (#46415)
Signed-off-by: muhammadfawaz1 <135441198+muhammadfawaz1@users.noreply.github.com>
Co-authored-by: Mahad Durrani <114791389+mahadrehmann@users.noreply.github.com>
2026-07-09 17:46:29 +08:00
Alexis K. 40cc2e8327 [Bugfix] Return HTTP 422 for unprocessable image URLs instead of 500 (#47165)
Signed-off-by: Alexis Kinsella <alexis.kinsella@gmail.com>
2026-07-06 11:56:23 +00:00
Muhammad FawazandMahad Rehmann 1bf149f334 Filter Pydantic-internal markers from validation error param (#46457)
Signed-off-by: muhammadfawaz1 <135441198+muhammadfawaz1@users.noreply.github.com>
Co-authored-by: Mahad Rehmann <114791389+mahadrehmann@users.noreply.github.com>
2026-06-23 13:20:50 +00:00
Muhammad FawazandMahad Durrani 69bdd34542 [Bugfix] Fall back to Pydantic loc for param in validation errors (#46038)
Signed-off-by: professorsab <135441198+professorsab@users.noreply.github.com>
Co-authored-by: Mahad Durrani <114791389+mahadrehmann@users.noreply.github.com>
2026-06-19 19:11:11 +08:00
Zang Peiyu 25ee659db0 Fix parallel_tool_calls: null treated as false instead of default true (#44955)
Signed-off-by: factnn <166481866+factnn@users.noreply.github.com>
2026-06-15 21:14:10 +00:00
Ekagra Ranjanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> e0b9fb1290 [ASR] Optimize CPU preproc to get 2.5x RTFx via multi-threading (#44612)
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-11 21:05:11 -07:00
wang.yuqi d01d0b4646 [Frontend] Consolidate online serving utils. (#44479)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-04 06:49:31 +00:00