baonudesifeizhai c3868bbbe4 [compile] Add FlashInfer FP8 async TP fusion and preserve allreduce fusion ordering #27893 (#39505) ...

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>

2026-05-01 05:08:34 +00:00

..

fusion

[compile] Add FlashInfer FP8 async TP fusion and preserve allreduce fusion ordering #27893 (#39505)

2026-05-01 05:08:34 +00:00

ir

Fix multiline-format string for python 3.10 (#38739)

2026-04-02 03:19:35 +00:00

utility

fused qknorm+rope kernel optimization for SM9.0 (#37376)

2026-04-12 19:58:37 -07:00

__init__.py

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

fx_utils.py

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731)

2026-02-06 04:19:49 -08:00

inductor_pass.py

[Core] Cache InductorPass.hash_source with functools.cache (#39328)

2026-04-20 14:06:15 -04:00

pass_manager.py

[ROCm] Add MLA dual RMS norm fusion (Q, KV) pass for DeepSeek/Kimi-K2 (#39242)

2026-04-20 14:56:27 +00:00

vllm_inductor_pass.py

[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)

2026-03-31 22:15:05 -04:00