Mickaël Seznec a597a57595 [Attention] Flash Attention 3 - fp8 (#14570) ...

Signed-off-by: Mickael Seznec <mickael@mistral.ai>

2025-03-20 01:14:20 -04:00

..

fused_moe

MI325 configs, fused_moe_kernel bugfix (#14987)

2025-03-18 08:05:18 -07:00

mamba

[MODEL] Add support for Zamba2 models (#13185)

2025-03-18 08:56:21 -07:00

quantization

[Attention] Flash Attention 3 - fp8 (#14570)

2025-03-20 01:14:20 -04:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

activation.py

[Neuron] Add custom_ops for neuron backend (#13246)

2025-02-25 11:47:49 -08:00

layernorm.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

linear.py

[Kernel] Add ModelOpt FP4 Checkpoint Support (#12520)

2025-03-12 05:13:11 +00:00

logits_processor.py

[Misc][Platform] Move use allgather to platform (#14010)

2025-03-03 15:40:04 +08:00

pooler.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

rejection_sampler.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

resampler.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

rotary_embedding.py

[Attention] Remove slow setattr in MLA (#14769)

2025-03-13 21:31:14 +00:00

sampler.py

[Misc] Remove dangling references to SamplingType.BEAM (#13402)

2025-02-17 19:52:35 -08:00

spec_decode_base_sampler.py

[model][refactor] remove cuda hard code in models and layers (#13658)

2025-02-24 06:10:14 -08:00

typical_acceptance_sampler.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

utils.py

[V1] Optimize handling of sampling metadata and req_ids list (#13244)

2025-02-18 12:15:33 -08:00

vocab_parallel_embedding.py

[CORE] [QUANT] Support for GPTQModel's dynamic quantization per module override/control (#7086)

2025-02-12 09:19:43 -08:00