amirkl94 6b7a81185d

Bugfix: Cutlass FP8 FusedMoE bad scaling factors (#27255) ...

Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2025-11-05 06:06:06 -05:00

..

basic_correctness

[Fix] Skip record_sleep_state logic in PrometheusStatsLogger if not in dev mode (#27789)

2025-10-30 19:26:27 +00:00

benchmarks

Feature/video support in random mm dataset (#25963)

2025-10-29 18:24:52 +08:00

compile

[Misc][qwen2_5_vl][torch.compile] Enable supports_torch_compile on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)

2025-10-28 22:36:43 +00:00

config

[MM][Core] Decouple ViT backend from LM backend (#27061)

2025-10-21 00:30:10 -07:00

cuda

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

detokenizer

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

distributed

[Bugfix] Fix allocation & free logic of SingleWriterShmRingBuffer (#27117)

2025-10-28 15:01:24 +00:00

engine

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

entrypoints

[Model, Core] Support Granite Speech & LoRA for STT (#24455)

2025-11-05 08:33:48 +01:00

evals

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

kernels

Bugfix: Cutlass FP8 FusedMoE bad scaling factors (#27255)

2025-11-05 06:06:06 -05:00

kv_transfer

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

lora

Load tuned fused_moe_lora shrink and expand kernel configs separately (#27435)

2025-11-04 18:27:35 +08:00

model_executor

[CI/Build] Fix amd model executor test (#27612)

2025-10-28 08:58:11 +00:00

models

[Bugfix] Fix encoder-only model support for transformers backend (#28021)

2025-11-04 22:24:41 -08:00

multimodal

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

plugins

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

2025-10-23 14:46:18 +00:00

plugins_tests

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

2025-10-23 14:46:18 +00:00

prompts

…

quantization

Support using Int4PreshuffledTensor after loading (#26066)

2025-11-04 06:00:57 -05:00

reasoning

[Refactor] Lazy-loaded reasoning_parser (#28092)

2025-11-05 15:37:02 +08:00

samplers

[CI] Replace large models with tiny alternatives in tests (#24057)

2025-10-16 15:51:27 +01:00

standalone_tests

[CI/Build] Move pre-commit only scripts to tools/pre_commit (#27657)

2025-10-29 08:04:33 +00:00

system_messages

…

tokenization

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

tool_use

[Refactor] Lazy import tool_parser (#27974)

2025-11-04 10:10:10 +08:00

tools

[CI/Build] Move pre-commit only scripts to tools/pre_commit (#27657)

2025-10-29 08:04:33 +00:00

tpu

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355)

2025-10-15 02:51:16 +00:00

transformers_utils

[Bugfix] Skip gs:// model paths for speculator detection (#27846)

2025-11-03 14:31:03 +00:00

utils_

[Misc] Clean up utils (#27552)

2025-10-27 09:05:40 +00:00

v1

[Hybrid allocator + kv connector] revert connector test changes related to hybrid allocator (#28011)

2025-11-05 10:36:31 +00:00

vllm_test_utils

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

weight_loading

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

__init__.py

…

ci_envs.py

[Model][0/N] Improve all pooling task | clean up (#25817)

2025-10-13 16:44:50 +08:00

conftest.py

[V0 deprecation] Remove VLLM_USE_V1 usage in most modules (#27955)

2025-11-04 20:51:16 -08:00

test_config.py

[UX] Support nested dicts in hf_overrides (#25727)

2025-10-07 11:19:16 +08:00

test_embedded_commit.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_envs.py

[Frontend] [gpt-oss] Mcp type bug (#27689)

2025-10-29 10:01:32 +00:00

test_inputs.py

[Bugfix] Fix SHM cache initialization (#26427)

2025-10-09 02:48:04 -07:00

test_logger.py

[torch.compile] Enable attention and allreduce fusion without custom ops enabled (#24604)

2025-10-17 08:10:23 -06:00

test_outputs.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_pooling_params.py

[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524)

2025-10-30 12:13:05 +00:00

test_regression.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_routing_simulator.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_scalartype.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_seed_behavior.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_sequence.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_triton_utils.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_version.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_vllm_port.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

utils.py

Adds anthropic /v1/messages endpoint to openai api_server (#27882)

2025-11-01 12:45:42 -07:00