Jinzhen Lin ee52d9901d [Quantization] support logical_widths for fp8 marlin (#30962) ...

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

2025-12-20 12:02:57 -08:00

..

assets

[VLM] Add Qwen3-VL generation test (#25185)

2025-10-29 12:19:37 +00:00

attention

[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869)

2025-12-20 09:03:35 +08:00

benchmarks

[Misc] support nsys profile for bench latency (#29776)

2025-12-18 14:52:20 +00:00

compilation

[Bugfix][torch2.10] Fix test_qwen2_5_vl_compilation with 2.10 RC (#30822)

2025-12-18 08:23:31 -08:00

config

[Model] Add MiMo-V2-Flash support (#30836)

2025-12-19 17:17:03 +00:00

device_allocator

[Core][AMD] Migrate fully transparent sleep mode to ROCm platform (#12695)

2025-11-12 15:24:12 -08:00

distributed

[NIXL][BUG FIX] Fix both failing issue and accuracy issue with nixl + host_buffer on CUDA (#30419)

2025-12-18 22:10:02 +00:00

engine

[Bugfix] Read truncate_prompt_tokens from pooling_params in AsyncLLM.encode() (#31013)

2025-12-20 10:29:31 +00:00

entrypoints

[Frontend][Bug] allow tool calls in analysis channel (#28139)

2025-12-19 10:47:44 +00:00

inputs

Strengthen input validation and tests for 'parse_raw_prompts’. (#30652)

2025-12-18 19:51:58 +00:00

logging_utils

[Misc] Colorize logs (#29017)

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

lora

fused_moe_lora PDL improvements (#30716)

2025-12-17 19:55:00 -08:00

model_executor

[Quantization] support logical_widths for fp8 marlin (#30962)

2025-12-20 12:02:57 -08:00

multimodal

Add hidden dimension validation for multimodal embedding inputs (#30968)

2025-12-19 07:59:36 +00:00

platforms

[ROCm][CI][Bugfix] Multi-Modal Model Support Fixes and Attention Backend Improvements (#30270)

2025-12-19 02:17:27 +00:00

plugins

[Frontend] Resettle pooling entrypoints (#29634)

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

profiler

[Logs] Optimize startup logs 4 (#29903)

2025-12-13 16:12:53 -05:00

ray

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

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

reasoning

Adapt the old parameter enable_thinking in chat_template_kwargs (#30852)

2025-12-17 07:10:59 -08:00

third_party

fix some typos (#24071)

2025-09-02 20:44:50 -07:00

tokenizers

Adapt the old parameter enable_thinking in chat_template_kwargs (#30852)

2025-12-17 07:10:59 -08:00

tool_parsers

GLM-4.7 Tool Parser and Doc Update (#30876)

2025-12-20 00:09:58 +00:00

transformers_utils

Check for truthy rope_parameters not the existence of it (#30983)

2025-12-18 13:59:10 -08:00

triton_utils

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

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

usage

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

utils

[Refactor] Refactor for DeepGemmQuantScaleFMT using cache (#30898)

2025-12-19 13:50:39 -07:00

v1

[Bugfix] Read truncate_prompt_tokens from pooling_params in AsyncLLM.encode() (#31013)

2025-12-20 10:29:31 +00:00

vllm_flash_attn

[BugFix] Fix vllm_flash_attn install issues (#17267)

2025-04-27 17:27:56 -07:00

__init__.py

[V0 Deprecation] Remove V0 executors (#27142)

2025-10-21 11:09:37 -07:00

_aiter_ops.py

[ROCm] Serving Fails on Radeon Due to AITER Dtype Import (#30952)

2025-12-18 11:47:46 +00:00

_bc_linter.py

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

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

_custom_ops.py

[MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990)

2025-12-19 13:09:54 -08:00

_ipex_ops.py

[Multimodal][XPU]Enable vision attn backend for xpu platform (#27525)

2025-11-01 04:45:02 +00:00

beam_search.py

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

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

collect_env.py

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

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

connections.py

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

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

env_override.py

[CI] Reorganize compile tests so new tests are automatically included in CI (#28625)

2025-11-19 06:13:50 -08:00

envs.py

Make engine core client handshake timeout configurable (#27444)

2025-12-19 20:38:30 +00:00

forward_context.py

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

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

logger.py

Make the httpx logger less annoying when Transformers v5 is installed (#30480)

2025-12-11 15:44:56 +00:00

logits_process.py

[Misc] Refactor tokenizer interface (#29693)

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

logprobs.py

[Core] Switch Flat logprob control from environment variable to SamplingParams (#28914)

2025-11-19 02:10:02 +00:00

outputs.py

[Model] Add num_cached_tokens for PoolingRequestOutput (#27378)

2025-10-23 14:03:42 +08:00

pooling_params.py

add add_truncate_prompt_tokens in repr for PoolingParams (#29683)

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

py.typed

Add py.typed so consumers of vLLM can get type checking (#1509)

2023-10-30 14:50:47 -07:00

sampling_params.py

[Misc] Refactor tokenizer interface (#29693)

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

scalar_type.py

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

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

scripts.py

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

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

sequence.py

Fix IntermediateTensors initialization and add type hints (#28743)

2025-11-15 04:31:36 +00:00

tasks.py

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

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

tracing.py

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

version.py

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

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