Lucas Wilkinson 95501a70ec

[BugFix] Fix DeepSeek-R1 hang with DP and MTP (#30119) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>

2025-12-09 18:51:19 +00:00

..

assets

…

attention

[Feature] Batch invariant: Enable TRITON_MLA without prefix-caching (#29125)

2025-12-08 19:31:57 -05:00

benchmarks

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

compilation

[BugFix] Fix non detected failing tests (#30277)

2025-12-09 17:57:55 +00:00

config

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

device_allocator

…

distributed

kv_transfer: Rename the shared storage connectors (#30201)

2025-12-08 20:46:09 -08:00

engine

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

entrypoints

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

inputs

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

logging_utils

[Misc] Colorize logs (#29017)

2025-11-19 19:26:04 -05:00

lora

[Misc] Fix safetensors import for safe_open (#30300)

2025-12-09 06:50:06 +00:00

model_executor

[Feature] Batch-Invariant Support for FA2 and LoRA (#30018)

2025-12-09 10:01:38 -05:00

multimodal

[v1] Add PrefixLM support to FlexAttention backend (#27938)

2025-12-07 15:51:36 +00:00

platforms

[ROCm] Aiter Quant Kernels (#25552)

2025-12-09 14:27:37 +00:00

plugins

[Frontend] Resettle pooling entrypoints (#29634)

2025-12-01 15:30:43 +08:00

profiler

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

ray

[Small] Capture AttributeError when checking ray dependency. (#29024)

2025-11-20 22:54:10 -08:00

reasoning

[Structured Output][Reasoning] Improves decoding throughput for models using single-token reasoning endings. (#30056)

2025-12-09 18:54:08 +08:00

third_party

…

tokenizers

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

transformers_utils

[Bugfix] Skip generation config fallback for GGUF to prevent multi-process hang (#30209)

2025-12-09 01:52:43 +00:00

triton_utils

[mypy] Enable type checking for more directories (#29674)

2025-11-28 08:39:27 -08:00

usage

…

utils

[Bugfix] Fix DeepGEMM after #29546 (#30267)

2025-12-09 01:05:27 +00:00

v1

[BugFix] Fix DeepSeek-R1 hang with DP and MTP (#30119)

2025-12-09 18:51:19 +00:00

vllm_flash_attn

…

__init__.py

…

_aiter_ops.py

[ROCm] Aiter Quant Kernels (#25552)

2025-12-09 14:27:37 +00:00

_bc_linter.py

…

_custom_ops.py

[bugfix][quantization] Fix fp8 per_tensor scale shape (#30257)

2025-12-09 19:28:50 +08:00

_ipex_ops.py

…

beam_search.py

…

collect_env.py

…

connections.py

…

env_override.py

…

envs.py

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

forward_context.py

[BugFix] Fix assert batch_descriptor.num_tokens == num_tokens_padded (#30173)

2025-12-09 10:36:12 -05:00

logger.py

[BugFix] respect VLLM_LOGGING_LEVEL in logger (#29761)

2025-12-02 07:49:16 +00:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

logprobs.py

…

outputs.py

…

pooling_params.py

add add_truncate_prompt_tokens in repr for PoolingParams (#29683)

2025-11-28 08:41:05 -08:00

py.typed

…

sampling_params.py

[Misc] Refactor tokenizer interface (#29693)

2025-11-29 04:02:21 -08:00

scalar_type.py

…

scripts.py

…

sequence.py

…

tasks.py

…

tracing.py

…

version.py

…