4 people 579aef4e8d [ROCm] Bump AITER to 0.1.21.post1 (#52826) ...

Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Signed-off-by: fai <fangzhouai@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: fai <fangzhouai@gmail.com>

2026-09-03 16:28:40 -07:00

..

assets

…

benchmarks

[Bugfix] Reject tokenless chat and audio streams (#54708)

2026-09-01 11:24:19 -04:00

compilation

[Core][MRV2] Freeze gc during V2 CG capture; skip per-descriptor cleanup (#54646)

2026-08-31 19:37:46 -07:00

config

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

cute_utils

…

device_allocator

[Core] Release NCCL communicator memory in sleep mode (#51485)

2026-09-01 14:31:16 +08:00

distributed

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

engine

[Bugfix] Account for PCP in multi-node world size validation (#55111)

2026-09-03 10:52:42 +00:00

entrypoints

Use server-generated keys for late-interaction query caches (#51445)

2026-09-03 07:15:58 +00:00

inputs

[Feat][MM Hashing] include media_io_kwargs in multi-modal hashes (#54241)

2026-09-01 13:17:01 +00:00

ir

…

kernels

…

logging_utils

…

lora

[LoRA] Cleanup VocabParallelEmbedding (#53843)

2026-08-26 16:19:35 +08:00

model_executor

[ROCm] Bump AITER to 0.1.21.post1 (#52826)

2026-09-03 16:28:40 -07:00

models

[Perf] Prefetch the weight before the PDL wait in fused_q_kv_rmsnorm (#55020)

2026-09-03 15:40:16 -07:00

multimodal

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

parser

[Bugfix] Implicitly close DeepSeek DSML parameters (#54838)

2026-09-02 14:13:36 +08:00

platforms

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

plugins

…

profiler

[Profiler] Fix start_profile permanently no-op after max_iterations auto-stop (#51839)

2026-08-25 08:13:29 -04:00

ray

…

reasoning

feat: Add support for reasoning_token_count to reasoning parser (#54982)

2026-09-03 05:02:49 -07:00

renderers

[warmup] overlap renderer warmup and engine core initialization (#54557)

2026-09-03 19:44:21 +00:00

third_party

[Kernel] Warm up Qwen GDN gated RMSNorm (#54251)

2026-09-03 18:19:48 +08:00

tilelang_utils

…

tokenizers

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

tool_parsers

[Model] Add K2-Horizon model support (#55063)

2026-09-03 01:17:08 -07:00

tracing

…

transformers_utils

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

triton_utils

[Bugfix][CPU] Fix several bugs (#54042)

2026-08-31 15:33:06 +08:00

usage

…

utils

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

v1

[warmup] overlap renderer warmup and engine core initialization (#54557)

2026-09-03 19:44:21 +00:00

vllm_flash_attn

…

__init__.py

…

_aiter_ops.py

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

_custom_ops.py

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

_xpu_ops.py

[XPU] Add fused GemmaRMSNorm path for eager execution (#53678)

2026-09-03 06:11:20 +08:00

collect_env.py

…

connections.py

…

env_override.py

…

envs.py

[Frontend] Gate scale-out endpoints behind opt-in flag (#54579)

2026-09-02 14:31:14 +08:00

exceptions.py

[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management (#49445)

2026-08-31 14:26:49 +00:00

forward_context.py

…

logger.py

…

logits_process.py

…

logprobs.py

[Bugfix] Handle empty FlatLogprobs slices and delta output (#53704)

2026-08-26 21:00:54 +08:00

model_inspection.py

…

outputs.py

…

pooling_params.py

…

py.typed

…

sampling_params.py

[Bugfix] Reject empty bad-word tokenizations (#53433)

2026-08-31 12:07:17 -07:00

scalar_type.py

…

scripts.py

…

sequence.py

…

tasks.py

…

version.py

…