16 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
wang.yuqi c1692c85f1 [Misc] mv chat_utils.py to renderers. (#60522)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-10-10 06:50:34 +00:00
Chauncey fa5cfd48d5 [Refactor] Deduplicate trace header handling in BaseServing (#60828)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-10-10 05:27:58 +00:00
TyroneandHarry Mellor 7867d6c52d [Frontend] Name the served models in the model-not-found 404 (#59889)
Signed-off-by: TyroneNel <71038642+TyroneNel@users.noreply.github.com>
Signed-off-by: TyroneNel <Tyrone.Nel@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-10-04 20:45:51 +00:00
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 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
erdholionandIlir 131e0285f6 [Frontend] Warn when removed guided-decoding fields are present in a request (#54285)
Signed-off-by: Ilir <ljeci.ilir@gmail.com>
Co-authored-by: Ilir <ljeci.ilir@gmail.com>
2026-09-04 16:15:40 +00:00
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
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
Martin Hickey 0a31372e5f [Frontend] Add detokenization streaming derender for disaggregated serving (#47301)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
2026-07-29 18:01:20 -07:00
wang.yuqi a14f57a3ac [Frontend] Refine the entrypoint class's inheritance hierarchy. (#47498)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-07-03 10:50:06 +00:00
wang.yuqi 3483240b7e [Frontend] Consolidate scale out entrypoints (#44512)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-29 03:18:53 -07:00
wang.yuqi 31ca9504b1 [Frontend] Split ServingRender into renderer and entrypoint. (#44285)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-23 11:19:09 +00:00
wang.yuqi 1eb2cc961e [Frontend] Refactor ServingTokenization entrypoint. (#46022)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-06-22 06:27:58 +00:00