Colin Zandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 27ffbfde8d Fused Shared Expert Support for AMD Quark DeepSeek-V4 Model Checkpoints (#48044) ...

Signed-off-by: Colin Zeng <Colin.Zeng@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-07-23 00:34:17 +00:00

..

assets

[Bugfix] Align OpenCV video metadata timeline (#47099)

2026-06-30 20:43:42 +00:00

benchmarks

[Bugfix] Re-enable benchmarking of librispeech dataset. (#47033)

2026-07-08 16:19:26 +00:00

compilation

[ROCm] Remove redundant AITER fused_qk_rmsnorm probe (avoids config-time HIP init) (#47992)

2026-07-21 22:58:14 -05:00

config

[ROCm] Remove redundant AITER fused_qk_rmsnorm probe (avoids config-time HIP init) (#47992)

2026-07-21 22:58:14 -05:00

cute_utils

[Bugfix] Fix broken NVVM caused by CuteDSL 4.6.0 (#49108)

2026-07-19 19:45:56 -07:00

device_allocator

[Core] Make sleep-mode backend capability flags communicator-agnostic (#47243)

2026-07-01 07:17:44 +00:00

distributed

[PD][Bugfix] Fix NIXL hybrid MLA+mamba heterogeneous TP (#49297)

2026-07-22 07:11:39 +00:00

engine

[Misc] Remove old now unsupported max_num_partial_prefills and max_long_partial_prefills (#49244)

2026-07-21 08:52:52 +00:00

entrypoints

[Frontend] Parallelize preprocessing within the same request for pooling models online serving. (#49153)

2026-07-22 10:56:23 +00:00

inputs

[Render][Speculator] Add return_loss_mask to render endpoint for training data generation (#46846)

2026-06-28 00:07:33 -07:00

ir

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

kernels

[Kernel][Helion] Disable warp specialization in rms_norm_per_block_quant B200 configs (#48797)

2026-07-17 21:39:09 +00:00

logging_utils

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00

lora

[Model] Add Inkling LoRA support [4/N] (#48884)

2026-07-17 09:52:15 +08:00

model_executor

[Bugfix] Fix DeepGEMM warmup when using FlashInferFp8DeepGEMMDynamicBlockScaledKernel (#49467)

2026-07-22 16:28:49 -07:00

models

Fused Shared Expert Support for AMD Quark DeepSeek-V4 Model Checkpoints (#48044)

2026-07-23 00:34:17 +00:00

multimodal

[Misc] Move PyNvVideoCodec stuff out of gpu worker (#49322)

2026-07-22 10:11:56 +08:00

parser

[Bugfix][Parser] Fix special tokens (EOS/BOS) leaking into reasoning content (#48748)

2026-07-22 16:10:55 -04:00

platforms

[Bugfix] Fix WSL circular import from pin_memory warning_once (#48444)

2026-07-20 18:30:55 -07:00

plugins

[Frontend] Add endpoint plugins framework (#47454)

2026-07-08 10:00:41 +08:00

profiler

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

ray

Propagate Flash Attention cache configuration to Ray workers (#49177)

2026-07-21 07:47:53 +00:00

reasoning

[Model] Add Inkling model support [1/N] (#48799)

2026-07-15 23:40:07 -07:00

renderers

[Bugfix][Renderer] Rebuild vision chunk UUIDs in async render path (#49400)

2026-07-22 14:11:24 +00:00

third_party

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

tokenizers

[Bugfix] Fix logprobs token-string collision from SentencePiece space… (#48674)

2026-07-20 12:17:18 +08:00

tool_parsers

[Bugfix][Tool Parser] Preserve whitespace in parameter values (MiniMax M2, Qwen3, MiniCPM5 XML) (#48846)

2026-07-17 16:45:41 +00:00

tracing

…

transformers_utils

[Bugfix] Retry config read to survive concurrent HF cache refresh (#49001)

2026-07-22 15:35:38 -07:00

triton_utils

[ROCm][Bugfix] Fix use_v2_model_runner inside Ray driver thread (#45998)

2026-06-24 08:41:56 +08:00

usage

replace cuda_device_count_stateless() to current_platform.device_count() (#37841)

2026-03-31 22:32:54 +08:00

utils

[copy of #45208] CuMem slept-L1 fragmentation accounting (#49208)

2026-07-20 23:08:11 +00:00

v1

[BugFix] Handle per-group prefix-hit divergence for hybrid models with KV connector (#48425)

2026-07-22 17:19:11 -07:00

vllm_flash_attn

[CI/Build][Docker] Bump nvidia-cutlass-dsl to 4.6.0 and drop packaging workarounds (#47442)

2026-07-16 13:51:41 +00:00

__init__.py

…

_aiter_ops.py

[ROCm] Remove redundant AITER fused_qk_rmsnorm probe (avoids config-time HIP init) (#47992)

2026-07-21 22:58:14 -05:00

_custom_ops.py

[Bugfix][CI] Fix topk_softplus_sqrt no-op on non-XPU platforms (#49452)

2026-07-22 15:36:17 -07:00

_xpu_ops.py

[XPU][DeepSeekV4]Add DeepSeek-V4 fuse_index_q SYCL kernel path (#45991)

2026-07-21 21:22:34 +08:00

collect_env.py

[XPU]Enhance environment collection for Intel XPU and optimize layout (#35698)

2026-04-13 12:51:46 +08:00

connections.py

[CI] Add retry with 4x backoff to HTTP fetches for transient failures (#37218)

2026-03-19 19:00:20 +00:00

env_override.py

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

2026-06-16 15:16:45 +02:00

envs.py

[Bugfix] Exclude location-derived path vars from torch.compile cache factors (#47573)

2026-07-22 16:56:09 -07:00

exceptions.py

[Bugfix] Return HTTP 422 for unprocessable image URLs instead of 500 (#47165)

2026-07-06 11:56:23 +00:00

forward_context.py

[Feature] Support sequence parallel without the need for DP, 1.9%~5.0% E2E Throughput Improvement (#47070)

2026-07-05 05:41:30 -07:00

logger.py

[Log] Log once in local node by default (#37568)

2026-03-19 12:04:59 -07:00

logits_process.py

…

logprobs.py

…

model_inspection.py

…

outputs.py

[Front-end] [Messages] Populate num_cache_creation_tokens (#48535)

2026-07-18 13:04:35 -04:00

pooling_params.py

[Bugfix] Reject removed pooling parameters (#48984)

2026-07-19 05:18:03 -07:00

py.typed

…

sampling_params.py

[Frontend] Expose logprob_token_ids on Python OpenAI endpoints (#43463)

2026-07-13 14:40:21 -07:00

scalar_type.py

Humming support for 2/3/5/6/7-bit pack-quantized weight-only inference (#46389)

2026-06-24 13:53:54 -04:00

scripts.py

…

sequence.py

[Core] Cleanup KVConnector handling with PP + fix MRV2 (#43732)

2026-05-28 13:12:03 -07:00

tasks.py

[Bugfix] Reject removed pooling parameters (#48984)

2026-07-19 05:18:03 -07:00

version.py

…