| 1234567891011121314151617181920212223242526272829303132333435 |
- # Fixes found by profiling (2026-09-27): FlashInfer's per-step rollback clone,
- # the indexer's fp32 head-gate GEMM, a switch for the fused mHC kernel's token
- # limit, and a Triton sparse MLA kernel in place of FlashInfer's FA2 path
- # (VLLM_TRITON_SPARSE_MLA=1, about 3.3x faster on GB10). kda.py and
- # causal_conv1d.py: the KDA short conv writes q, k and v as separate dense
- # tensors, so FlashKDA no longer copies them (~51 ms per 16k-token step).
- # kv_cache_*.py, worker_utils.py, warmup.py: the drafter's KV gets its own
- # small pool, paged 256 tokens at a time, instead of a page in every KV block
- # (VLLM_GLM5NEXT_DRAFT_POOL=1, VLLM_GLM5NEXT_DRAFT_BLOCK_SIZE).
- # tilelang_kernels.py and mhc_tilelang.py: the fused mHC decode kernel reads
- # its projection weights (hc_*_fn, stored bf16 in the checkpoint) as a cached
- # bf16 copy instead of the model's fp32 one, which halves its weight reads and
- # leaves every product unchanged.
- services:
- glm53:
- volumes:
- - ../experimental/fixes/_fa_common.py:/usr/local/lib/python3.12/dist-packages/flashinfer/mla/_batch_mla/_backends/_fa_common.py:ro
- - ../experimental/fixes/attention.py:/usr/local/lib/python3.12/dist-packages/vllm/models/glm5next/common/attention.py:ro
- - ../experimental/fixes/tilelang_kernels.py:/usr/local/lib/python3.12/dist-packages/vllm/model_executor/kernels/mhc/tilelang_kernels.py:ro
- - ../experimental/fixes/mhc_tilelang.py:/usr/local/lib/python3.12/dist-packages/vllm/model_executor/kernels/mhc/tilelang.py:ro
- - ../experimental/fixes/flashinfer_mla_sparse_sm90.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/mla/flashinfer_mla_sparse_sm90.py:ro
- - ../experimental/fixes/gb10_sparse_mla.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/mla/gb10_sparse_mla.py:ro
- - ../experimental/fixes/gdn_attn.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/gdn_attn.py:ro
- - ../experimental/fixes/kda.py:/usr/local/lib/python3.12/dist-packages/vllm/models/glm5next/common/kda.py:ro
- - ../experimental/fixes/causal_conv1d.py:/usr/local/lib/python3.12/dist-packages/vllm/model_executor/layers/mamba/ops/causal_conv1d.py:ro
- - ../experimental/fixes/kv_cache_utils.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/core/kv_cache_utils.py:ro
- - ../experimental/fixes/kv_cache_coordinator.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/core/kv_cache_coordinator.py:ro
- - ../experimental/fixes/kv_cache_interface.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_cache_interface.py:ro
- - ../experimental/fixes/worker_utils.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/utils.py:ro
- - ../experimental/fixes/warmup.py:/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu/warmup.py:ro
- environment:
- - VLLM_MHC_FUSED_MAX_TOKENS=${VLLM_MHC_FUSED_MAX_TOKENS:-32}
- - VLLM_TRITON_SPARSE_MLA=${VLLM_TRITON_SPARSE_MLA:-1}
- - VLLM_GLM5NEXT_DRAFT_POOL=${VLLM_GLM5NEXT_DRAFT_POOL:-1}
- - VLLM_GLM5NEXT_DRAFT_BLOCK_SIZE=${VLLM_GLM5NEXT_DRAFT_BLOCK_SIZE:-}
|
