3 people 9da56fd18b [Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986) ...

Cherry-picked from https://github.com/vllm-project/vllm/pull/41986

Plumb SwiGLU clamp limit through DeepGemm FP8/W4A8 MoE quant configs
and experts. Extend silu_mul_per_token_group_quant_fp8_colmajor with
clamp support and forward the limit on all FP8/MXFP8/MXFP4 paths.

Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

Signed-off-by: khluu <khluu000@gmail.com>

2026-05-14 12:38:36 -07:00

..

basic_correctness

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

benchmarks

[Bench] Forward --seed to CustomDataset and CustomMMDataset shuffle (#40788)

2026-05-04 00:39:10 +00:00

compile

Fix mypy failure on main (#42197)

2026-05-10 07:55:57 +00:00

config

[Perf] FP8 FlashInfer Attn for ViT (#38065)

2026-04-27 13:44:15 +08:00

cuda

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

detokenizer

[CI/Build] Remove use of skip_v1 (#34699)

2026-02-18 12:19:11 +08:00

distributed

[Kernel] Pack output and LSE in DCP A2A (#41160)

2026-05-01 09:01:17 -04:00

engine

Handle optional bool-or-string CLI args in get_kwargs (#40951)

2026-05-09 19:47:21 -07:00

entrypoints

[Frontend][Bugfix] Abort ASR engine requests on cancellation (#41266)

2026-05-09 23:51:11 -07:00

evals

[Eval][CI] Add basic mrcr eval to tests/evals/ (#40164)

2026-05-01 12:00:38 -04:00

ir

[vLLM IR] 2/N fused_add_rms_norm and maybe_inplace overload (#36823)

2026-05-01 23:41:15 -04:00

kernels

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 12:38:36 -07:00

lora

[LoRA] Initial EP support for LoRA (#40867)

2026-05-09 00:31:23 -07:00

model_executor

[Models][Gemma3/Gemma4] Support hidden_act variants in gated MLP (#40588)

2026-05-08 11:29:11 -07:00

models

Fix Molmo2 image token metadata (#42162)

2026-05-11 01:19:21 +00:00

multimodal

[Bugfix] use served_model_name for multimodal error message (#41003)

2026-04-27 08:22:35 -07:00

parser

Fix Qwen3 streaming content routing (#40820)

2026-05-06 17:22:01 -04:00

plugins

[Misc] Reorganize inputs (#35182)

2026-03-25 10:22:54 -07:00

plugins_tests

[CI/Build] Skip Prithvi/Terratorch model-registry tests when terratorch is missing (#41389)

2026-04-30 12:47:55 -07:00

prompts

[BugFix] Fix input positions for long context with sliding window (#2088)

2023-12-13 12:28:13 -08:00

quantization

[Quantization] Add ModelOpt NVFP4 W4A16 (4-bit weights, fp16/bf16 activations) support (#41769)

2026-05-09 21:15:50 +00:00

reasoning

[Bugfix] KimiK2ReasoningParser: guard against buffered end-token in streaming (#41068)

2026-05-04 17:42:05 +00:00

renderers

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

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

rocm/aiter

[ROCm][CI] Cleaning and restructuring amd-ci legacy pipeline (#34839)

2026-03-19 14:30:58 -05:00

samplers

[Frontend] Add Support for MM Encoder/Decoder Beam Search (Offline) (#36153)

2026-03-06 01:16:56 -08:00

standalone_tests

Add structure to requirements/ directory (#39024)

2026-04-10 13:46:41 -07:00

system_messages

[V1] Implement Cascade Attention (#11635)

2025-01-01 21:56:46 +09:00

tokenizers_

[Mistral Tokenizer] allow more leniency in apply_chat_template (#41658)

2026-05-05 19:56:15 -07:00

tool_parsers

[Bugfix] Preserve leading/trailing whitespace in GLM non-streaming tool parser (#42026)

2026-05-08 21:49:15 -07:00

tool_use

[Refactor] Consolidate required/named tool_choice streaming into DelegatingParser (#41876)

2026-05-07 09:50:59 -07:00

tools

build: embed image provenance metadata in vLLM containers (#40653)

2026-04-29 03:07:41 -07:00

tracing

[CI][Tracing] Fix race condition by adding server readiness check (#34364)

2026-02-16 12:57:39 +00:00

transformers_utils

[Bugfix] Fix _CONFIG_REGISTRY types getting wrong config class when on-disk model_type differs (#39554)

2026-04-20 19:04:48 -07:00

utils_

[Bugfix] Fix spawn_new_process_for_each_test silently swallowing test failures (#41423)

2026-05-06 11:17:15 -04:00

v1

[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)

2026-05-14 00:59:51 -07:00

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

[Sparse24] [Deprecation] Remove Sparse24 CT integration and kernels (#36799)

2026-03-23 16:03:29 -04:00

__init__.py

[Small] Formatter only checks lints in changed files (#1528)

2023-10-31 15:39:38 -07:00

ci_envs.py

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

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

conftest.py

[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)

2026-05-14 00:59:51 -07:00

test_access_log_filter.py

[Logging] add --disable-access-log-for-endpoints CLI option (#30011)

2026-01-26 21:49:03 +00:00

test_attention_backend_registry.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

test_config.py

[Bug] Fix status update address for non-MOE model within external dp mode (#40839)

2026-05-04 16:37:16 -07:00

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

fix(security): Add VLLM_MAX_N_SEQUENCES environment variable and enforce limit (#37952)

2026-03-27 09:02:10 -04:00

test_fxgraphcache_pickle_patch.py

[ZenCPU] Make PT Backport Patch Accessible to vLLM (#38205)

2026-04-10 08:29:35 +00:00

test_inputs.py

[Refactor] Pass full VllmConfig to Renderer (#34485)

2026-02-12 22:48:38 -08:00

test_jit_monitor.py

[Feature] Add Triton kernel JIT compilation monitor for inference (#40137)

2026-05-05 14:08:57 +04:00

test_logger.py

[BugFix] respect VLLM_LOGGING_LEVEL in logger (#29761)

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

test_logprobs.py

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

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

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

[Model] Deprecate the score task (this will not affect users). (#37537)

2026-03-20 08:07:56 +00:00

test_ray_env_utils.py

[Feat][Executor] Introduce RayExecutorV2 (#36836)

2026-04-01 14:34:29 -07:00

test_ray_env.py

[Ray] Propagate third-party env vars to Ray workers via prefix matching (#34383)

2026-02-17 01:08:42 -08:00

test_regression.py

[CI/Build] Use modelscope's international site for regression test (#42176)

2026-05-09 19:47:09 -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

test_zen_cpu_platform_detection.py

In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)

2026-03-15 23:35:35 +00:00

utils.py

[Bugfix] Fix LOGITPROC_SOURCE_ENTRYPOINT test to use spawn-compatible dist-info registration for XPU/ROCm (#42040)

2026-05-09 12:32:04 +08:00