3 people 7e33081cee [Attention] Make FlexAttention and FlashAttention use num-blocks first layouts (#42095) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

2026-05-26 19:55:56 -07:00

..

assets

[Examples][last/6] Resettle examples. (#41084)

2026-05-07 19:42:12 -07:00

benchmarks

[Misc] Support interleaved custom image benchmark datasets (#43636)

2026-05-26 03:37:25 -07:00

compilation

[Kernel] Porting fuse_minimax_qk_norm to manual fusion (#43410)

2026-05-26 13:16:03 -07:00

config

[Kernel] Porting fuse_minimax_qk_norm to manual fusion (#43410)

2026-05-26 13:16:03 -07:00

cute_utils

[GDN] GDN Prefill kernel for SM100 (#43273)

2026-05-26 14:02:11 +08:00

device_allocator

[Bugfix] Make CuMemAllocator free callback stream-aware (#43020)

2026-05-22 03:36:22 +00:00

distributed

[Attention] Make FlexAttention and FlashAttention use num-blocks first layouts (#42095)

2026-05-26 19:55:56 -07:00

engine

[GDN] GDN Prefill kernel for SM100 (#43273)

2026-05-26 14:02:11 +08:00

entrypoints

[Bugfix][V1] Fix TOCTOU race causing intermittent EADDRINUSE on multi-API-server DP startup (#42585)

2026-05-26 14:06:00 -07:00

inputs

feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720)

2026-05-01 10:05:55 +08:00

ir

[Perf] Set IR Op Priority Once at Worker Init (#42631)

2026-05-15 15:56:13 +00:00

kernels

[ROCm][CI] Fix ROCm LoRA Transformers fallback with full CUDA graphs (#41577)

2026-05-23 04:31:32 +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

[XPU] Fix fused MoE LoRA kernel crash on XPU by using platform-agnos num_compute_units (#43646)

2026-05-26 03:40:32 -07:00

model_executor

[Perf] Optimize Fp8BlockScaledMMLinearKernel input_scale tensor using new_empty() (#43677)

2026-05-26 19:55:52 -07:00

models

[DSv4] Drop _get_compressed_kv_buffer in DeepseekCompressor (#43690)

2026-05-26 10:11:25 -07:00

multimodal

[Perf][4/n] Eliminate various GPU<->CPU syncs (#42347)

2026-05-19 10:35:54 -04:00

parser

[Bugfix] Fix reasoning dropped on streaming boundary deltas (#42691)

2026-05-23 16:18:30 -07:00

platforms

[Attention] Make FlexAttention and FlashAttention use num-blocks first layouts (#42095)

2026-05-26 19:55:56 -07:00

plugins

[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)

2026-04-09 10:09:45 +00:00

profiler

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

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

ray

…

reasoning

Fix: Nemotron 3 rescue whitespace-only final_content, not just None (#41846)

2026-05-10 02:07:58 +00:00

renderers

[Frontend] Add truncation side to OpenAI endpoints (#43260)

2026-05-21 20:32:31 -07:00

third_party

…

tokenizers

[Frontend] Rework fastokens integration (#43168)

2026-05-21 15:36:58 -07:00

tool_parsers

[Bugfix] Fix glm4_moe_tool_parser._is_string_type for /v1/responses FunctionTool format (#39601)

2026-05-20 22:58:59 -07:00

tracing

…

transformers_utils

[CI] De-flake test_models for bigscience/bloom-560m (#43197)

2026-05-21 06:30:14 +00:00

triton_utils

[CPU] Experimentally enable Triton and MRV2 (#43225)

2026-05-22 01:48:17 -07:00

usage

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

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

utils

[CPU] Experimentally enable Triton and MRV2 (#43225)

2026-05-22 01:48:17 -07:00

v1

[Attention] Make FlexAttention and FlashAttention use num-blocks first layouts (#42095)

2026-05-26 19:55:56 -07:00

vllm_flash_attn

[Attention] use diff kv backend for mimo v2 flash (#40045)

2026-04-24 11:25:55 +00:00

__init__.py

Remove bc-lint (#35274)

2026-02-26 03:01:01 -08:00

_aiter_ops.py

[ROCm][Bugfix] Fix fused_mla_dual_rms_norm for AITER API rename _fused_qk_rmsnorm (#42606)

2026-05-15 14:50:03 -06:00

_custom_ops.py

[Kernel] Remove NormGateLinear (#43554)

2026-05-25 09:49:19 +00:00

_tilelang_ops.py

[Kernel] Add mhc_pre_big_fuse_with_norm_tilelang (#43474)

2026-05-25 01:19:45 +00:00

_xpu_ops.py

[XPU] Enable multiple key kernels for sparse attention (#37888)

2026-05-22 12:02:51 +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

Revert "[torch.compile] Add patch for fullgraph compilation" (#42686) (#42913)

2026-05-18 09:02:51 -04:00

envs.py

[Misc][Refactor][ROCm] Convert MoRI-related envvars to extra config args (#43303)

2026-05-26 03:33:35 -07:00

exceptions.py

[openapi server] log exception in exception handler(2/N) (#36201)

2026-03-10 20:16:30 -07:00

forward_context.py

[Perf] Set IR Op Priority Once at Worker Init (#42631)

2026-05-15 15:56:13 +00:00

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

Revert "[Core] Replace routing replay with device cache and async D2H pipeline" (#39917) (#42434)

2026-05-13 23:49:01 -07:00

pooling_params.py

[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)

2026-05-22 18:43:33 +08:00

py.typed

…

sampling_params.py

[Reasoning] [Bugfix] Reject invalid thinking_token_budget values (#43402)

2026-05-26 03:37:30 -07:00

scalar_type.py

…

scripts.py

…

sequence.py

[Model Runner V2][Minor] Simplify PP logic (#38031)

2026-03-24 13:57:17 -07:00

tasks.py

[Frontend] Remove frontend pooling multi task support. (#37861)

2026-04-21 12:27:44 +00:00

version.py

…