5 people 867fd5e8ed [ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184) ...

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Tan Pin Siang <tanpinsiang@gmail.com>

2026-06-27 10:22:57 +00:00

..

attention

[ROCm][Bugfix] Fix chunk alignment when using context parallelism with TRITON_MLA (#46114)

2026-06-25 00:07:28 -04:00

fla

[Perf][KDA] Fuse gate softplus, chunk-local cumsum, and RCP_LN2 scaling (#43667)

2026-05-28 13:47:08 +00:00

fused_moe

[ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184)

2026-06-27 10:22:57 +00:00

fusion

Fix docs build on main (#45536)

2026-06-13 08:53:23 -07:00

mamba

fix(quantization): Fix AWQ dequantize on Intel XPU and refactor AutoAWQ config (#42727)

2026-06-18 20:12:28 +08:00

minimax_rms_norm

[Model]Fix MiniMaxM2ForCausalLM perf regression (#45935)

2026-06-22 00:28:52 +08:00

pooler

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

quantization

[NVFP4][Emulation] Fuse NVFP4 weight dequantization with compute in triton kernel for w13/w2 MOE MLP linears (#44667)

2026-06-25 19:33:00 -07:00

rotary_embedding

fix: guard flash-attn rotary import (#42679)

2026-06-11 08:43:31 -04:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

attention_layer_base.py

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

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

batch_invariant.py

[Feature] Support batch invariant rms norm with residual (#42453)

2026-06-03 15:22:01 -04:00

conv.py

[Misc] Always use forward_mulmat for Conv3d on newer versions of torch. (#38487)

2026-03-30 05:39:41 +00:00

fused_allreduce_gemma_rms_norm.py

[Model] Add MiniMax M3 support (#45381)

2026-06-16 01:01:25 +08:00

fused_qk_norm_rope.py

[Perf] fuse qk rmsnorm rope gate for qwen3.5 (#44176)

2026-06-09 22:12:17 +08:00

layernorm.py

[Kernel] Add weightless RMSNorm CUDA kernels for has_weight=False (#41430) (#44109)

2026-06-16 23:45:55 -07:00

lightning_attn.py

[Kernel][Test] Extend lightning_attn and awq_triton kernel tests to XPU (#43307)

2026-06-04 14:25:59 -04:00

linear.py

fix(quantization): Fix AWQ dequantize on Intel XPU and refactor AutoAWQ config (#42727)

2026-06-18 20:12:28 +08:00

logits_processor.py

[PluggableLayer][3/N] Apply PluggableLayer to llm_head and vocab embedding layer (#33465)

2026-04-10 16:12:59 +08:00

mhc.py

[ROCm][DSV4] Disable TileLang MHC dispatch on gfx942 (#45931)

2026-06-22 09:26:54 +00:00

mla.py

[bugfix]Indexer init skip and MTP TopK share for iteration (#45895)

2026-06-19 09:57:51 +08:00

resampler.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

sparse_attn_indexer.py

[GLM5.2 Perf] fused_indexer_q_rope_quant triton kernel, 1.9% ~ 3.3% E2E Throughput improvement. (#46862)

2026-06-26 22:16:20 -07:00

utils.py

[ZenCPU] Add zencpu Platform Runtime Logging and Docs (#42726)

2026-06-16 08:23:12 -04:00

vocab_parallel_embedding.py

[Migration] Migrate GGUF quantization support to plugin (#39612)

2026-06-12 12:02:21 -07:00