Khushali Desai 23ab0cfdbc speculative decoding under tensor parallelism (TP>1) , workspace creation select max hidden dim of target and draft model (#52193) ...

Signed-off-by: khushali9 <khushali.desai9@gmail.com>

2026-08-24 21:33:36 +00:00

..

distributed

speculative decoding under tensor parallelism (TP>1) , workspace creation select max hidden dim of target and draft model (#52193)

2026-08-24 21:33:36 +00:00

ir

…

__init__.py

…

test_double_aiter_rms_quant_fusion.py

…

test_functionalization.py

…

test_fuse_act_padding.py

…

test_fuse_mla_dual_rms_norm.py

…

test_fusion_attn.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_fusion.py

Remove VLLM_TEST_FORCE_FP8_MARLIN to replace with linear_backend/moe_backend (#52182)

2026-08-18 12:58:04 -04:00

test_mla_attn_quant_fusion.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_mla_rope_kvcache_cat_fusion.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_noop_elimination.py

…

test_pass_manager.py

…

test_qk_norm_rope_fusion.py

…

test_rmsnorm_reshape_fusion.py

…

test_rocm_aiter_qk_norm_rope_kvcache_fusion.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_rope_kvcache_fusion.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_scatter_split_replace.py

…

test_silu_mul_quant_fusion.py

…

test_split_coalescing.py

…

test_vllm_fusion_pattern_matcher_pass.py

…