147 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 bd70a61c20 [Mini-VLLM] Remove orphan subsystems: snapshot, CPU workers, dead decoders
- Delete the snapshot package, CLI command, and its launch tests
- Delete CPU workers, cpu_communicator, and the hw_agnostic layer package
- Delete the EC CPU connector, keeping the EC base glue intact
- Delete dead composite/triton_flashinfer backends and third_party/flashmla
- Delete dead video decoders, video-bound tests, and orphan utils
- Remove the deep_gemm_mega_moe option and dead allreduce fusion pair

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 09:27:06 +07:00
MOVZXandHinata 2b544b7ba0 [Mini-VLLM] Cut dead subsystems across serving, connectors, parsers
- Remove P/D transfer connectors: nixl, nixl_chat, mooncake x2, hf3fs,
  moriio, hisparse, example and hidden-states connectors
- Reduce weight_transfer to the base API used by model loading
- Remove kv_offload tiering, simple_kv_offload, ec cpu/example,
  snapshot command, engine snapshot server
- Remove transformers model fallback, dsv4 tokenizers, dead platforms
  cpu/tpu/xpu, flashmla third_party, dsa, megamoe/flydsl, dead attn
  ops, dead layers (short_conv, fused_embed_norm, indexer_topk,
  relu2 gemma_ar, lightning_attn, minimax_rms_norm), gemm_rs_ar
- Keep MoE LoRA op (imported eagerly by punica_gpu); drop fp8 variant
- Rebuild parser hubs around Qwen3 adapters only (36 dead adapters)
- Remove dead tests with the code they covered

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-19 02:19:03 +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
MOVZX e0fe5df731 Merge branch 'main' into patches 2026-10-17 08:06:56 +00:00
71c20f73f2 [FlashInfer] Migrate autotune warmup to flashinfer.autotune_v2 managed cache (#55671)
Signed-off-by: Yang Xu <yanxu@nvidia.com>
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Signed-off-by: YangXu <yanxu@nvidia.com>
Co-authored-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
2026-10-17 02:08:28 +00:00
28e92eeff2 [ROCm][Perf][Kimi-K3] Use AITER Gluon chunk_kda for KDA prefill (#59552)
Signed-off-by: Omar Muhammad <omar.muhammad@amd.com>
Signed-off-by: Nicholas Susanto <nicholas.susanto@amd.com>
Co-authored-by: Nicholas Susanto <nicholas.susanto@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-16 22:58:56 +00:00
Ayushman Singh de7eeaa87b [Perf] Share Triton JIT warmup compilation pool across registered kernels (#61422) 2026-10-16 08:59:42 -04:00
MOVZX be95edb7f6 Merge branch 'main' into patches
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-16 17:35:42 +07:00
4d58fa254a [MoE] Unify DeepGEMM MegaMoE experts behind one feature-matrix layer; add NVFP4 (#61538)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 19:02:01 +00:00
MOVZX 76df77c04e Merge branch 'main' into patches
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-15 21:16:39 +07:00
0951fc183c [ROCm][DSv4.1] Disambiguate ROCm attention class names (#58689)
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 21:38:39 +08:00
simon-veitner-redhatandClaude ae94e9c9e8 [Bugfix] Don't crash DeepGEMM MegaMoE warmup when get_bf16_mega_gate_config is missing (#61657)
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-10-14 18:58:35 +00:00
253e02b95e [Perf] Warm up DeepGEMM MegaMoE kernels before serving (#60468)
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
2026-10-13 20:17:48 +08:00
Nick Hill 3fe917abb1 [Bugfix][MRV2] Fix FlashInfer attention and ReplaySSM warmups on MRV2 (#61013)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-10-11 16:04:41 -07:00
f2376cdc4d [Fast Start] Preload the FlashInfer autotune table on the weight cache daemon (#60085)
Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
2026-10-10 15:48:06 +00:00
Wentao Ye 3709632ff2 [Refactor] Remove dead code multiple places (#60120)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-10-10 15:41:10 +00:00
SeongJun LeeandIsotr0py 699c892dd5 [Perf] Skip the M-RoPE warmup when every holder of the RoPE fuses it (#60246)
Signed-off-by: lesj0610 <lesj0610@gmail.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
2026-10-10 06:47:39 +00:00
MOVZX ac305c44cb Merge branch 'main' into patches
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-09 17:41:13 +00:00
Jiahan Chang (Cyrus) 816173ca9d [Kernel] Remove WAR for LL CuTeDSL BF16 GEMM (#60434)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
2026-10-08 05:38:07 +00:00
fba462e008 [Bugfix]Fix FlashInfer warmup crash: autotune(tuning_buckets=...) must round M up, not down (Invalid MXFP8 split-K tactic with spec-decode) (#58165)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 14:01:21 -04:00
3403e0f176 [Bugfix] Persist FlashInfer autotune cache per rank to fix the rank-0-only cache-hit deadlock (#57635)
Signed-off-by: Madhav Jivrajani <madhav.jiv@gmail.com>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
2026-10-06 17:51:01 +00:00
Chris LeonardandShengqi Chen cc73cca9c8 [Build] Migrate vendored DeepGEMM from pybind to TORCH_LIBRARY (abi3) (#48962)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
2026-10-06 08:39:04 -07:00
edfccc9469 [ROCM][Perf] Add ROCM_SEGMENTED_ATTN attention-backend works across RDNA3/3.5/4 (#59132)
Signed-off-by: root <jeffaw99@hotmail.com>
Signed-off-by: big-yellow-duck <jeffaw99@hotmail.com>
Co-authored-by: Tan Pin Siang <1716735+tanpinsiang@users.noreply.github.com>
Co-authored-by: vllmellm <190700713+vllmellm@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-06 07:53:47 +00:00
MOVZX 2877121b2d Merge remote-tracking branch 'upstream/main' into patches
Signed-off-by: MOVZX <movzx@yahoo.com>
2026-10-03 21:59:03 +07:00
24df2d3fc7 [Model] Add Qwen4Exp to the Qwen GDN Triton warmup (#56742)
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
2026-10-02 21:38:15 +08:00
08d77cad7b [Bugfix] Gate Kimi-K3 KDA warmup on sys.modules to skip Kimi import for non-Kimi models (#59257)
Signed-off-by: YueshenZ <YueshenZ@users.noreply.github.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: YueshenZ <YueshenZ@users.noreply.github.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
2026-10-01 09:25:45 +00:00
Andrii SkliarandAndrii Skliar deb148e730 [Mamba] Add FlashInfer ReplaySSM support for MTP (#52928)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
2026-09-30 21:41:17 +00:00
VenkyandClaude Opus 5.5 42f0c17ea7 [Bugfix][PP][Spec Decode] MiniMax-M3 EAGLE3 aux-state relay at PP > 1 and per-stage FlashInfer autotune (#57197)
Signed-off-by: venkywonka <23023424+venkywonka@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-01 01:14:24 +04:00
lesj0610 521235d6df Merge remote-tracking branch 'origin/main' into sync/lesj/qwen4exp-bugfixes
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-27 18:25:21 +09:00
Misha GoinandCodex 71891bdb94 [Perf] Parallelize registered CUDA Triton kernel warmup at startup (#58582)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-24 19:52:00 -04:00
lesj0610 045467c102 Merge remote-tracking branch 'origin/main' into sync/lesj/qwen4exp-bugfixes
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-23 00:40:48 +09:00
f92b78f6ef [Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2026-09-22 01:07:17 -07:00
lesj0610 5780c0125a Merge remote-tracking branch 'origin/main' into sync/lesj/qwen4exp-bugfixes
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-20 09:27:57 +09:00
Jiahan Chang (Cyrus)andOpenAI Codex 4e5ffda19d [Bugfix] Isolate supplemental FlashInfer BF16 autotuning (#57285)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-17 07:38:58 +00:00
Lucas Wilkinson bd2d7ae7c1 [Perf] Reuse MoE workspace for DeepGEMM warmup (#57268)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-09-17 03:01:19 -04:00
lesj0610 6c5552776b Merge remote-tracking branch 'origin/main' into lesj/qwen4exp-bugfixes
Both sides edited the same import block in the Qwen4Exp NVIDIA and AMD
models and nothing else collided. This branch adds
`from ..common.mtp import make_mtp_hidden_buffer`, the helper the MTP
buffer extraction calls; upstream ec4a3a5370 widened the `..config`
import to `ATTENTION_LAYER_TYPES, QSA_LAYER_TYPE, Qwen4ExpConfig` for the
layer-type constants it introduced. The two changes are independent, so
the resolution keeps both lines. Every symbol still has a use outside the
import in both files.

Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-17 08:16:59 +09:00
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
lesj0610 a66a3e1b4e Merge remote-tracking branch 'origin/main' into sync/lesj/qwen4exp-bugfixes
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-14 14:36:05 +09:00
Woosuk Kwon 3b533197a9 [Perf] Parallelize mHC pre-norm JIT warmup (#56683)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-09-13 18:58:20 -07:00
lesj0610andClaude Opus 5 3b1911c0ca [Bugfix][Model] Fix Qwen4Exp MTP buffer placement, config parsing, and Triton warmup
Three initialization and config defects found serving Qwen4Exp, each with a
regression test.

**The MTP hidden buffer lands on the ambient device.** torch.empty for the
spec-decode hidden buffer takes no device, so it follows whatever device is
current rather than vllm_config.device_config.device. The allocation was
duplicated verbatim in the NVIDIA and AMD backends; it moves to
common/mtp.py so the two cannot drift, and the caller passes is_last_rank
rather than reaching for the process group from shared code.

**M-RoPE keys are reported as unrecognized.** Qwen4Exp drives M-RoPE through
mrope_section and mrope_interleaved, which transformers' rope validator does
not know for rope_type="default", so every load warns about a configuration
the model genuinely uses. Declare them at rope validation on the text config
and on the outer config that mirrors it; every other key still warns.

**transformers' layer_types spelling is unread.** Its Qwen4Exp config
canonicalizes "full_attention" entries to "qwen_sparse_attention" in memory,
so checkpoints re-exported through it serialize that name. vLLM keys QSA off
"full_attention" plus indexer_n_heads, so map the spelling back.

**Qwen4Exp is missing from the Triton warmup set.** Its GDN prefill and QSA
run on other backends, but the kernels this warmup covers -- the gated RMS
norm, the causal conv, the post-conv preparation, the decode state update --
are Triton whichever prefill kernel is chosen, so they compile on the first
prompt instead. qwen4_exp_mtp stays out: kernel_warmup passes the worker's
own model_config, which is the target model's.

tests/models/qwen4_exp/test_config.py: 15 passed.
tests/model_executor/test_qwen_triton_warmup.py: 6 passed.
ruff check, ruff format --check and mypy (Python 3.10) report what they
already report on the base commit.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
2026-09-14 07:25:01 +09:00
Kevin H. Luu dec0b5d63f [Bugfix] Skip Triton autotune inspection without Triton (#56676)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-13 17:05:29 +00:00
Roberto L. CastroandCodex e52be1a62d [9/N][warmup][DSv4] Migrate MHC TileLang kernels (#50178)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
2026-09-12 17:25:23 -07:00
aed894c190 [6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-12 17:24:24 -07:00
7ee8a6dd01 [watermarking] Dual-key gumbel-max watermarking for speculative decoding support (#56122)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
2026-09-12 18:42:01 +00:00
Ayushman Singhandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 7bcca16729 [Bugfix] Fix DeepGEMM FP8 warmup coverage (#56452)
Signed-off-by: Ayushman Singh <40520701+ayush1399@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-12 14:20:38 -04:00
Itay Alroy 658c8131c7 [Elastic EP] Reuse CUDA graphs across reconfiguration (#54985) 2026-09-12 10:26:39 -04:00
d43bb2f37f [3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Matthew Bonanni <matthew@neuralmagic.com>
Signed-off-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-09-12 00:36:47 -04:00
Roberto L. CastroandCodex 120ec4ebd2 [5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
2026-09-12 00:05:59 -04:00