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

..

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_table.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

gpu_input_batch.py

[BugFix][V1] Fix overhead related to bad_words sampling when not in use (#14894)

2025-03-16 14:53:34 -07:00

gpu_model_runner.py

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

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

gpu_worker.py

[V1] Move OOM check into sampler run (#14728)

2025-03-13 20:40:23 -07:00

lora_model_runner_mixin.py

[Kernels] LoRA - Retire SGMV and BGMV Kernels (#14685)

2025-03-18 09:47:53 +00:00

tpu_model_runner.py

[V1][TPU] Support V1 Sampler for ragged attention (#14227)

2025-03-19 21:00:39 -07:00

tpu_worker.py

[V1] TPU - Add tensor parallel support via Ray (#13618)

2025-03-08 08:19:38 -05:00

worker_base.py

[v1] fix parallel config rank (#13445)

2025-02-18 12:33:45 +08:00