- mm_fp8 accepts 3D operands through the same signature: grid.z slices by batch strides, size-1 batches broadcast (stride 0), inner .t() views fold into the layout tag at zero copy
- fix _LinearFp8 backward crash on 3D [B,L,d] training inputs (flatten before mm_fp8, reduce grad_b over leading dims)
- expose kRasterGroup/kStreamOut as template knobs; drop the 64x128 mid CTA and staged crosswise-B path from dispatch (direct wins everywhere re-measured, including DRAM-streamed B)
- dispatch thresholds grounded in fresh sweeps: m<=64 -> 64x64 CTA (+27% at 64x8192x2048), small-CTA crossover at SM*14/3 total tiles (+13% at 96 tiles), threshold counts batch x per-matrix tiles (+31% at 64x512^3 bmm, +25% at 8x1024x2048)
- remove scripts/tools/bench_fp8_gemm.py (superseded by csrc/tests/fp8_sweep.cu for kernel-level tuning)
Benchmark: NVIDIA L20, E4M3, NT pre-quantized, median of 100-200 iters
- 64x8192x2048: 29.1 -> 22.8 us (94 TF/s)
- 1024x1536x2048: 67.4 -> 59.6 us (108 TF/s)
- bmm 64x512^3: 139.8 -> 106.7 us; bmm 8x1024x2048: 186 TF/s
- regression-free: 4096^3 192 TF/s, 8192^3 200 TF/s, 512^3 unchanged
- parameterize warp tile (WarpM/WarpN) in Fp8GemmTraits; MMA loops, fragment arrays and epilogue scale with kMt/kNt instead of the fixed 64x32/4x4, enabling cuBLAS-style 64x64 CTAs of 32x32 warps
- dispatch by output tiling (grid-searched via csrc/tests/fp8_sweep.cu): fewer than 48 output tiles take 64x64/32x32 with a lean ring (4 CTAs/SM fill the wave-quantization gap: 512^3 goes 16 -> 64 CTAs); larger shapes keep 128x128 with the kStages+1 ring
- kStages+1 canonic ring rotation drops the post-compute barrier on the congruous path (one __syncthreads per k-tile); LeanRing keeps the kStages ring for the small CTA; direct-crosswise operands always rotate kStages+1 (their prefetch issues right after barrier 1 and would race a lean ring - caught by the pure C layout suite)
- stage the bf16 epilogue through the reclaimed operand smem: swizzled scatter + barrier + coalesced 16B copy-out replaces 8 disjoint 16B per-warp segments (~50% write efficiency before)
- hoist per-lane ldmatrix swizzle offsets out of the mainloop (stage-relative table + ring-base add) so the innermost loop stops recomputing IMAD/LOP3 address chains
- bypass the torch.library dispatch for real CUDA tensors in quantize/mm_fp8 wrappers (~5us/call, ~40% of a 512-wide call's wall time); fake/subclass tensors keep the custom_op route
vs the previous kernel + python path, wall clock on NT squares: 512^3 52 -> 13us (4.0x, 5.2 -> 20.5 TF, now 1.36x cuBLAS _scaled_mm), 1024^3 1.05x, 2048^3 1.02x (46.9 -> 48.2 TF kernel-only); correctness: 4 layouts x 6 shapes pure C suite PASS, 588 pytest PASS
- split quantize into quantize.cuh, templated on input type (bf16/fp16/fp32)
- rename pybind entry quantize_bf16 to quantize; validate the fmt enum
- fix fp8x2 packing: one 32-bit word packs two pairs (halves were dropped)
- drop the dead OutFp8 template param; GEMM output is always bf16
- fp8_state.reset() restores recipe/format defaults too (test state leak)
- rewrite tests for the two-primitive API with fp32-domain amax references
- g/x/w may each be bf16 or pre-quantized fp8 matching fmt; a pre-quantized operand skips its quantize kernel
- snapshot sx/sw/sg before the ring finalize overwrites the aliased scale slot so the gemm dequantizes with the quantize scale
- forward carries its scale to backward so gradients reuse the forward's scale
- grad_input/grad_weight forced bf16; a pre-quantized g dequantizes before the bias-sum
- regression test: two delayed steps with a changing amax must not leak the scale ratio
- Rotate kStages+1 canonical buffers for direct-crosswise operands so their load issues right after barrier 1 and its LDG+PRMT latency overlaps the MMA phase, instead of stalling the post-compute inter-barrier window (ncu on the production 24L/dim1536/ffn6912 shapes: barrier 3.7-4.1 + long-scoreboard 1.6-1.8 stalls per issue before).
- Split the stage loaders into load_async (cp.async operands, committed after the post-compute barrier) and load_direct (ring-indexed by tile, not stage, since the rings differ in depth).
On the production shapes vs cuBLASLt _scaled_mm: dX 1.11-1.24x (from 1.27-1.42x), dW 1.32-1.35x (from 1.26-1.49x); generic 4096/11008 shapes also improve (dX 37.6->40.8 TF, dW 36.0->37.3 TF). fp8 train step vs bf16: ~1.2x at both 512 and 2048 tokens.
- Finalize scale rings inside the quantize kernels: a last-block epilogue (threadfence + counter elect) folds amax into hist, reduces the window and publishes the next scale on device, zero extra launches; _ScaleRing packs [hist | scale | counter] into one CUDA buffer.
- Split FP8QuantizeParams out of FP8Params so each operator owns its fields; linear_forward/backward_fp8 take optional ring arguments.
- Drop the inference weight-quantization cache; the optimizer bumps the weight version every step, so a cache would miss anyway.
- Zero amax scratch via empty + cudaMemsetAsync instead of torch::zeros, cutting a ~50us fill_ dispatch per quantize.
- Stage crosswise-B operands K-major with cp.async (contract >= 8192) and PRMT-transpose per k_seg region in smem, interleaved with the MMAs; the sync LDG + byte-scatter path it replaces was long-scoreboard bound (ncu 4.6 vs 0.4 stalls/issue).
- Load crosswise-A direct with an in-register PRMT transpose; its operands are typically L2-resident and the staging round trip measured as a net loss.
- Enable grouped rasterization for the congruous NT forward (shared B stripe keeps the weight operand hot in L2) and make the smem budget layout-aware (Fp8GemmSmem) while holding two CTAs per SM.
- Annotate ops/fp8.py return types; drop weight-cache and decorator tests, hoist their imports to module level.
e2e 12L/dim1024/B4xT512 fused AdamW: fp8 137.8ms/step vs bf16 210.3ms, 1.53x. Kernel vs cuBLASLt _scaled_mm: fwd 1.03-1.09x, dX 1.33-1.47x, dW 1.30-1.39x (from 1.10/1.42-1.49/1.52-1.56x), before the pre-transposed copies cuBLASLt needs for dX/dW. fp8 train step vs bf16: 1.34x at 2048 tokens (was 1.25x), 1.08x at 512.
- last-block epilogue (threadfence + counter elect) folds amax into hist[idx], reduces the window and publishes the next scale on device — zero extra launches per linear layer
- _ScaleRing packs [hist | scale | counter] into one CUDA buffer; the eager hist-write / max / scale-copy chain and update() are gone
- split FP8QuantizeParams out of FP8Params so each operator owns its fields; linear_forward/backward_fp8 take optional ring arguments
- e2e 12L/dim1024/B4xT512 (fused AdamW): fp8 137.8ms/step vs bf16 210.3ms, 1.53x; fwd 1.82x, bwd 1.50x
- collapse FP8TensorMeta's 12 slots + 6 copy-paste methods into three _ScaleRing objects (hist/idx/scale/initialized + update/seed)
- skip meta allocation entirely on the DynamicScaling path (zero rings, scales measured inline)
- drop write-only FP8State._last_device and unused E4M3_MAX alias
- load_operand_tile ColMajor path issued one LDG then immediately scattered 16 byte-granular shared stores, so every store waited on the preceding global load; the runs of one row group now batch into registers first (v[kPasses]) and scatter after, overlapping the LDG latencies
- hoist pass-invariant predicates: the alignment check folds to one uniform (base | ld) & 15 test since r0 is always a multiple of 16, and rows_full leaves the per-pass condition; the contract tail zero-fills without global traffic
- RowMajor path hoists the row bound and the (invariant) chunk-alignment check out of the per-chunk loop
- measured (cuda events, old/new interleaved): crosswise bwd gemms +5-9%, RowMajor and fwd NT within noise; model step unchanged (in the 563-617 ms band)
- file passed through clang-format with the new .clang-format config
- linear_forward_fp8 accepts pre-quantized w8 (matching fmt) and skips the weight quantize; amax_w returns 0 on that path since no bf16 values are seen
- bias is now fused into the GEMM epilogue for both dtypes, replacing the separate torch-level add (one elementwise kernel per linear removed)
- FP8Params.bias becomes void* with a new bias_scale slot: null scale = raw bf16 bias, non-null = fp8 storage dequantized in the epilogue after the operand scaling and before any output quantization
- ops/fp8.py relaxes the w dtype check to bf16-or-fp8 and passes bias_scale through
- regression test covers w8/b8, w8/bf16-bias and the amax_w = 0 contract vs an explicit quantization reference
- backward used to read the global fp8 flag at loss.backward() time, so calling it outside fp8_autocast silently fell back to bf16 mm (953 ms cublas per step, 49.9% of the model step)
- _LinearFp8(torch.autograd.Function) now owns the fwd/bwd pair: forward captures fmt/recipe/meta on ctx inside the autocast region, backward reads only ctx (scales from the meta rings, masks from ctx.needs_input_grad), so backward is fp8 wherever it runs
- register the aten::linear impl on AutogradCUDA (replaces torch's generated linear formula that calls aten::linear_backward into the bf16 fallback) and keep the CUDA key for inference_mode
- drop the aten::linear_backward override and fp8_linear_backward (dead paths)
- regression test asserts the fp8 backward fires outside the autocast region and grads match the bf16 reference by direction/norm (E5M2 noise)
- model step (0.67B, CE loss, batch 4x1024): backward GEMMs 953 -> 618 ms (1.54x), full step ~1.2x
- K tile 32->64 (new default): fewer barriers, more MMA per stage; generalize tile_at swizzle and load_operand_tile accordingly
- 64x128 small-M CTA for m<=64 (2x at 64x4096x4096)
- L2 rasterization for crosswise-A layouts (+6..21%)
- micro-bench: NT 4096^3 +35%; linear fwd 1.24-1.76x, bwd 1.71-2.27x vs bf16
- add csrc/tests/fp8_test.cu (single MMA demo + GEMM layouts x K-tiles vs CPU reference)
- NSDMI null/-1 defaults for AttentionParams/FP8Params pointer+flag members: partially packed structs can no longer hold garbage non-null pointers that gate optional paths (root cause class of the paged test bug); still aggregates, still trivially copyable
- move per-lane ldmatrix wrappers (ldsm_x2/x4) from fp8/gemm.cuh to common/mma.cuh as ldmatrix_x2_lane/x4_lane, next to the single-address variants
- DEVICE_FORCEINLINE macro in common/mma.cuh (matches layout_policies.cuh, internal linkage)
- frag_addr now delegates to tile_at: the swizzle math has one source
- operand layouts as CUTLASS-style RowMajor/ColMajor tags threaded from launch_fp8_gemm through the kernel to load_operand_tile; B's operand view via transpose_layout_t; call sites read <Fmt, false, RowMajor, ColMajor> instead of <Fmt, false, false, true>
- paged decode test left new_k_ptr/new_v_ptr as stack garbage; PagedKV::decode_addr then took the new-KV path on wild pointers (illegal access or wrong last-token K/V)
- value-init the POD (= {}) at every construction site
- attention family -> astrai::attention; fp8 family -> astrai::fp8
- new common/reduce.cuh (warp/group reductions, atomic_max_float)
- new common/cp_async.cuh (predicated cp_async_16, commit/wait group)
- move MAX_SPLITS into attention/common.h; delete warp_utils.cuh
- .cu bindings and pure C tests open family namespaces via using
- 128x128 CTA of 8 warps x 64x32 warp tiles: 16 mma.sync per warp per K-segment (was 8)
- ldmatrix.x4/x2 with per-lane swizzled addresses replaces 36 scalar LDS per warp-tile step
- __launch_bounds__(256, 2) caps registers at 124 so two CTAs fit per SM
- fp8 linear vs bf16 cuBLAS: fwd 1.07x->2.65x, bwd 1.41x->2.65x by size, peak 31-33 TFLOPS
- loader.py: lazy/cached import; is_available defers the actual load; get_module raises on unavailable
- ops/{attention,rotary,fp8}: use get_module instead of touching private _modules or their own _mod() cache
- package-data: ship astrai.extension.lib *.so in built wheels (non-editable installs previously lost every kernel)
- add skip_no_fp8 (CUDA + fp8_mm kernel + cc 8.9+) to tests/conftest.py
- use skip_no_cuda / skip_no_kernel / skip_no_fp8 directly in test modules
- drop _GPU alias and tests.extension.conftest re-exports
- remove unused imports (Union in hf_adapter, make_grpo_config in data conftest)
- Add server.py --config serve.yaml; explicit CLI flags override YAML
- Add scripts/serve.sh and serve_runtime.py for the Compose lifecycle
- Template server/cpu ports and param mounts in docker-compose.yml
- Document schema in docs/developer/docker-serving.md and params guide
- Add tests for runtime parsing and server CLI merge logic
- Convert protocol and MoE test classes to plain functions
- Add real server/engine integration and generate_async tests
- Isolate test model per test and use pytest tmp_path
- Reset FastAPI engine state after inference tests
- Fix generate_async StopIteration handling on Python 3.12
- Fix HF adapter MoE dense/shared and Gemma qk_norm mapping
- Correct dev dependency httpx2 to httpx
- Add astrai.serialization.hf_adapter mapping LLaMA-style HF keys to AstrAI names (input_layernorm, gate_proj, MoE experts/shared_experts) with config aliases for dense and MoE (Mixtral/DeepSeek-V3) layouts; reject biased projections, mismatched head_dim and MLA
- Give AutoModel.from_pretrained weights_format=auto|astrai|hf with auto-detection; read sharded safetensors via model.safetensors.index.json
- Adapt preloaded weights/config in train_context and benchmark CLI
- extract preprocessing config factories into tests/data/factories.py
- keep conftest.py fixtures-only; stop importing builders from it
- promote temp_dir fixture to root conftest for cross-directory reuse
- unify duplicate BPE tokenizer builders into build_test_tokenizer
- merge grpo/dpo online e2e tests into one parametrized integration test
- extract engine mock factory and shared model batch builders
- drop local tempfile usage in favor of shared fixtures
No behavior change: 519 tests pass.
- avoid constructing model_fn more than once when reading config
- keep inference package exports focused on public entry points
- rename extra strategy arguments to strategy_kwargs
- scripts/train.sh load_infra() parses the top-level infra: section of TRAIN_CONFIG_FILE
- exports TRAIN_JOB_NAME/DATA/MODEL/CHECKPOINT_DIR/TRAIN_GPU_COUNT/CUDA_VISIBLE_DEVICES
- infra overrides .env.train via compose interpolation precedence; keys absent fall back
- train.yaml is now the single per-job config: host mounts, GPU filter, and hyperparameters
- requires host python3 with PyYAML when TRAIN_CONFIG_FILE is set; errors fail fast
- docs: docker-training.md documents the infra overrides and precedence
- route dX/dW through the fused 128x64 fast kernel via contiguous transposes
- drop the legacy 64x64 kernel, cutting dX 1.55->0.38 ms and dW 1.28->0.26 ms
- sync all threads after cp.async.wait_group to fix sporadic NaN in large GEMMs
- add fp8_mm_prequant_fp8 custom op for FP8-in/FP8-out GEMM
- keep training attention on dense 4d tensors
- use packed 3d tensors with KV cache for inference
- extend CUDA rotary embedding to packed 3d inputs
- adapt torch, CUDA and FlashAttention backend dispatch
- store page-table, request-row, and cache-location indices as int32
- preserve CUDA graph replay with bit-exact logits and KV cache coverage
- improve B=1 decode latency by 1-6% across 1K-32K contexts on L20
- amax for delayed scale was the quantized max (always ~448), so scale collapsed to 1
- this made fp8 gradients diverge (cosine 0.05) and training stall
- stop w/x transpose-quantize amax from polluting the grad scale
- fp8_ops is the only module touching the pybind (kernel interface)
- fp8.py keeps scaling state, delayed amax and aten::linear dispatch
- remove circular imports between old fp8_ops/fp8_state/fp8_dispatch
- dX/dW run as fp8 cublasLt gemms via fused transpose-cast
- shared (m,k,n) algo cache for fwd/bwd, mutex-protected
- bias add in-place on bf16 output, drop output copy
- pass w as param A (op=T) and x as param B (op=N) so the col-major [N,M] output storage is row-major C[M,N] directly, zero copy
- transpose_bias_cast kernel becomes a plain bias+write kernel
- fp8 e2e now beats bf16: 1.09x at M=4096, 1.06x at M=8192 (was 0.88x)
- cast gradients and inputs to weight.dtype instead of hardcoded bf16
- single code path covers bf16 and fp32 models, no branch needed
- gradient dtype now matches the leaf parameter dtype exactly
- register yaml 1.2 float resolver so scientific notation (2e-5) becomes float, not str
- replaces the decimal-point workaround in train configs
- add containerized training doc under docs/developer
- rewrite docker.sh with gpu default and --no-gpu override
- inject host uid/gid via ASTRAI_UID/GID in train.sh compose()
- filter readonly UID/GID lines when sourcing .env.train
- build image user via USER_UID/USER_GID args matching host uid/gid
- pass all GPUs (count: all) and filter by CUDA_VISIBLE_DEVICES inside the container
- forward NCCL vars through compose environment
- add a GPU trainer Compose profile with mounted data, models, and checkpoints
- add host commands for preflight, lifecycle, logs, status, and checkpoint cleanup
- resume from the latest complete checkpoint with external config or CLI arguments
- rename output pointer field o to o_ptr for consistency with q_ptr/k_ptr/v_ptr
- regroup AttentionParams fields by responsibility and fix misleading comments
- drop unused max_seq_len/total_q fields and paged decode max_seq_len arg
- drop redundant group_size param from decode launchers (computed from p)
- rename q_stride_* to q_*_stride to match mask stride convention
- rename mask_q_stride to mask_l_stride for consistent l-dim naming
- merge k/v and k_cache/v_cache into k_ptr/v_ptr; rename q to q_ptr
- KVSource policy selects contiguous vs paged mode at compile time
- fix scalar prefill head_dim=32 out-of-bounds via G=4 dispatch
- fix MMA decode 4D mask head indexing and invalid-row mask access
- add q_head/kv_head divisibility and head-dim contiguity checks
- validate split-KV scratch and decode out_buf layout in bindings
- set max dynamic shared memory for scalar decode D=256
- cover scalar prefill D=32 in pure C test
- route decode benchmark through InferenceEngine generate path
- add enable_cuda_graph toggle to engine, scheduler, and executor
- make benchmark --cuda-graph/--no-cuda-graph control the toggle
- hoist local time imports to module top
- Replace C++20 explicit lambda template parameters with file-scope structs (DecodeDispatch/PrefillDispatch etc.)
- Remove unused gs variable in run_decode_test
- Tighten paged test atol/rtol from 0.02 to 0.01 to match contiguous tests
- Match steady-state metadata to the active task IDs
- Rebuild request mappings for cached prefix pages
- Add regressions for batch refill and prefix reuse
- Eliminate core/ directory into cache/, runtime/, network/ subpackages plus flat modules
- Split cache.py (647 lines) into cache/{buffer,strategy,pool}.py by layer
- Add explicit ContiguousStrategy, make AllocationStrategy a real ABC
- Move TaskCacheState to cache/strategy.py, drop string forward references
- Rename api/ to network/, server.py to app.py
- Move sample.py into runtime/ alongside executor and graph
- Simplify TaskCacheManager.__init__ to single pool param
- Expose pool.strategy and pool.req_pool as public properties
- Fix KVCache import in attention_backend.py (TYPE_CHECKING guard)
- Fix steady-state decode reading uninitialized position_ids on first step
- TaskCacheRegistry -> TaskCacheManager (independent, held by scheduler)
- TaskCacheState co-locates 5 parallel dicts into one dataclass
- AllocationStrategy base class + PagedStrategy subclass (page_size is a parameter)
- _rollback() helper for unified cleanup (no duplicate free paths)
- Task._kv_len + prefill_done property (explicit, no output_tokens proxy)
- Steady-state detection single-sourced in TaskCacheManager.bind()
- PagePool is now pure physical layer (no task knowledge)
- Removed dead _page_to_hash dict in RadixCache
- drop Executor unused tokenizer field, _head_dim, stale metrics docstring
- unify greedy sampling via SamplingPipeline.sample, drop top-level duplicate
- drop Task.flush_remaining no-op and unreachable prompt-length branch
- drop ProtocolHandler redundant chunks list (reuse body)
- fix page_size=1 token-slot leak on task_free
- clear _task_pages/_task_slots on alloc-failure paths
- reset _bind_state on task_free to avoid stale steady-state reuse
- remove unreachable contiguous branches in paged-only helpers
- StreamingSeqDataset yields windows sequentially through each shard
- Shard-level shuffle, distributed and multi-worker shard partitioning
- __len__ returns total window count for scheduler total_steps
- Better OS page-cache locality than random-access map-style datasets
- cudaEvent.elapsed_time gives microsecond precision vs perf_counter
- cudaEvent measures actual GPU execution, not just kernel launch
- falls back to time.perf_counter on CPU-only devices
- 64-token prefill forward triggers cuBLAS auto-tuning at init
- reduces first-chat prefill from ~520ms to ~27ms
- warmup decode also drops from ~215ms to ~71ms
- move setup_logging to astrai/logging.py
- timed() now uses logger.isEnabledFor(DEBUG) instead of separate env var
- enable ASTR_LOG_LEVEL=DEBUG to see per-step timing logs
- call setup_logging() in stream_chat.py
- extract TaskTiming + MetricsCollector out of Task/TaskManager
- unify prefill/decode timing into single record() context manager
- expose avg_ttft_ms, avg_decode_tps, avg_e2e_latency_ms via /stats
- all three release builds (pure, cu128, cu130) produce the same .whl filename, causing uploads to overwrite each other
- append the CUDA tag as a local version label (e.g. +cu128, +cu130)
- move JSONL transform auto-creation from JsonlStore.load to DatasetFactory.load via _build_jsonl_transform helper
- remove TokenizeTransform and PipelineConfig imports from storage module
- JsonlStore.load now requires explicit transform= for eager mode
- DatasetFactory.load remains the public API with identical convenience behavior
- add _BindState dataclass and _is_steady_increment() to cache.py
- replace _bind_sig/_bind_seq_lens dual fields with single _bind_state
- replace DecodeSteadyState bare tuple with named dataclass
- use _is_steady_increment() in both PagePool.bind_tasks and Executor.execute_decode
- merge _generate_streaming/_generate_non_streaming into single _generate() with stream flag
- delete dead GenerationRequest class and generate_with_request method
- inline _next_token helper into generate_async
- replace flash-attn double-checked locking with functools.lru_cache
- extract _write_and_gather_kv helper shared by TorchNative/FlashAttn backends
- inline _kv_cache_is_contiguous into its sole call site in FlashAttnBackend
- change default backend priority from flash>cuda>torch to cuda>flash>torch
- add ASTR_BACKEND env var to override default backend at resolve time
- add supports_graph() static method to AttentionBackend ABC, override in CudaBackend
- replace isinstance(get_backend(), CudaBackend) with get_backend().supports_graph() in executor
- add torch.cuda.is_available() guard to CudaBackend.supports()
- Pre-allocate decode_out in InferenceWorkspace so attn_paged_decode does not call torch::empty inside graph capture
- Run live forward before graph capture to get valid output (graph pool memory is zeroed after capture block exits)
- Greedy generation with graph replay is bit-exact across all batch sizes
- _warmup_cuda_graphs pre-captures graphs at init for power-of-two batch sizes
- Graph enabled only when CudaBackend + supported head_dim + warmup succeeds
- Decode speedups vs no-graph: B=1 2.09x, B=4 1.80x, B=8 1.94x, B=16 1.76x
- Pre-allocate decode_out in InferenceWorkspace so attn_paged_decode does not call torch::empty inside graph capture
- Wire decode_out through KVCache, PagePool.bind_tasks, and CudaBackend.fwd_decode
- Run live forward before graph capture to get valid output (graph pool memory is zeroed after capture block exits)
- Greedy generation with graph replay is bit-exact across all batch sizes
- Decode speedups vs no-graph: B=1 2.09x, B=4 1.80x, B=8 1.94x, B=16 1.76x
- Decode with contiguous cache uses flash_attn_with_kvcache instead of materializing full KV via gather + flash_attn_func
- _backend_supports allows FlashAttnBackend for decode (q_len==1) even with explicit mask
- Decode speedups vs TorchNative (B=1,4,8,16 mean): cuda 1.55x, flash 1.40x, torch_native 1.00x
- Read K/V directly from flat pool via cache_batch_idx + cache_seqlens, zero-copy view reshape
- PagedKV::host_kv_len now returns max_context_len instead of max_seq_len
- Eliminates grid-z instability for CUDA graph capture/replay
- Restore skip_no_kernel re-export accidentally removed by ruff --fix
- Remove unused local variable b in attention_backend.py
- Remove unused variable rank0_sd in test_broadcast_state_dict.py
- Remove unused imports across test files
ViperEkura