Sujets / Linux
Linux
Auto topic: Linux
Issues
- #5949 [Engine] HIP/Linux: make HSA_USERPTR_FOR_PAGED_MEM=0 the default on discrete AMD cards
- #6531 [Benchmark] gfx1100 (RX 7900 XTX, IQ3_S): existing switches give 1.9–3.7x prompt and 1.2x decode speedup
- #6521 [Benchmark] R9700 + Threadripper PRO 3975WX: Hy4-Flash at ~30 tok/s (SQ-64, 4K) vs. 62 tok/s in the 0.2.18 notes
- #6523 [Engine] Windows NUMA in Strata: Why Our 40-Core Server Initially Used Only 20 CPU Workers
- #6526 [Engine] gfx1200 (2x RX 9060 XT, ROCm 10.1): peer-GPU fused WMMA prefill, RDNA4 MMVQ load_int_b2/Q6KTraits, and hipBLASLt fallback notes
- #6525 [Engine] Drop in MTP head replacement trained against quantized model output: +3.7 / +4.4 % decode at --spec 3
- #6339 [Engine] 0.1.62: --lookup-max-t past 8 with --draft dflash2 ends the request (dflash2: draft rows out of range); a small fix, +11..13 % on file rewrites
- #5614 [Engine] RX 9070 XT gfx1201: 0.1.58 verify unspecified launch failure triggers MES REMOVE_QUEUE GPU reset
- #6435 [Benchmark] RX 9070 (gfx1201, Windows 11, 32 GB RAM) / Gyro-S TQ1_0 / 0.2.6 → 0.2.17: 0.2.17 defaults lose ~30% prompt and ~12% decode on a 32 GB PC; two settings bring it back
- #6511 [Benchmark] 2x Tesla P40 (sm_61) split: 0.2.17 gives +9% decode, but 220K prefill is still ~5% under the 0.2.13.1 MMQ path (same-day A/B)
- #6515 [Engine] gfx12: `nw_barrier()` falls back to `__syncthreads()`, so the fused prompt experts' stage writes can race (latent)
- #6513 [Engine] Linux HIP: engine crashes at start (SIGSEGV in libamdhip64) with CachyOS's hip-runtime-amd 10.1 v3/znver4 builds; Arch's build works
- #6232 [Engine] 384K compaction re-reads 264K tokens (456 s): content-addressed, position-independent segment cache for near-zero-reread compaction
- #6074 [Engine] 0.1.60 prompt kernels: -13% at 20,000 tokens on a 16 GB card, +8% at 40,000, flat at 16,000
- #6500 [Engine] Vulkan backend: scope for the port (stage 1 landed: the loop and one Q4_0 kernel)
- #6327 [Engine] Compaction re-reads 331K-342K tokens five times (19.5-20.1 min each): the cache budget is the blocker (PR #4338)
- #5665 [GUI] Heavy typing lag inside the app window only; same UI smooth in browser (0.2.12, Wayland)
- #6496 [Other] Windows HIP rdna2 package (0.1.63) works on a real RX 6900 XT (gfx1030)
- #6493 [Engine] serve loop: GENI prompt can write past the position table; --cvec offsets unchecked (static analysis)
- #6491 [Other] Ray, an assistant and coding agent built on Strata: would any part of it help the app?
- #6487 [Engine] 0.1.62: --vision cpu fails deterministically at startup with "kv_stream: reset: an illegal memory access" (sm_86, Swift IQ3_S) — --vision gpu on the same box is fine
- #6409 [Engine] Qwen3.8-Next-Flash on Strix Halo AI Max 395 (128GB UMA): tuning for 2 concurrent streams at >100 tok/s each @ 200k context
- #6480 [Engine] qwen36 baked chat template breaks prompt reuse
- #6472 [Benchmark] RTX 4090 24 GB VRAM headroom for long-context KV and IQ4 experts
- #6470 [Engine] CUDA Q8_0 mmproj loses its VRAM saving with the native picture reader
- #6469 [GUI] The desktop agent's compaction request re-reads the conversation from the system prompt on Gyro (hybrid); --prompt-cache-spread cuts it from 14.9 to 2.7 s here
- #5953 [Engine] Qwen3.6-35B-A3B fails at startup on gfx1150 (Linux, ROCm 7.15): prefill gemm cublasGemmEx f16 - cuBLAS status 6
- #6429 [Benchmark] hipBLASLt tuning table by default on gfx1100 (RX 7900 XTX, IQ3_S): speed, decode and logits
- #6463 [Engine] Claude Code's small side requests evict the agent's parked conversation (default conversation cache)
- #6462 [Benchmark] RTX 4090 (sm_89): sm_86 bit-exact set +6%, sm_120 switches +4% on UD-Q4_K_XL, CPU share 32/6144 cuts 3K-token follow-up turns 26%
- #6461 [Engine] A tool parameter named `function` is dropped even when the tool declares it (Playwright MCP `browser_evaluate`), patch included
- #6460 [Engine] Claude Code auto-compaction returns an empty summary near the context limit unless `anthropic_thinking` is `on_request`
- #6459 [Engine] Codex CLI auto-compaction fails on /v1/responses: `compaction_trigger` input items are rejected (400)
- #5678 [Engine] Qwen3.8-Flash-Next IQ3_S on sm_121 (unified memory): prefill stalls at 33,372 of 33,379 tokens, just past the 32,768 chunk; STOP not honoured, restart never finishes
- #5917 [TUI] add custom access IP option
- #5990 [Engine] V100 (sm_70) on Linux: 13× Xid 79 + PCIe CmpltTO across engines 0.1.35–0.1.59.1 — not version-specific
- #6208 [Engine] 0.2.15 decodes 28-36% slower than 0.2.7 on RTX 3060 12 GB: --expert-cache auto starts with a much worse resident set (same pack and profile)
- #6445 [Engine] Abort on UR_RESULT_ERROR_DEVICE_LOST at the verify window (Intel Arc Pro B70, Linux)
- #6444 [Other] Linux - Build failed after update - .venv move to terminal broke pip
- #6077 [Engine] PLE: a VRAM hot tier for n-gram table rows, and stop pinning what is already resident
- #6118 [Engine] Cold 50K prefill regression: 0.1.52 → 0.1.59 → 0.1.60 on RTX 3060 12GB (−16.5%)
- #6160 [Engine] STRATA_PIPED_MTP is turned off on Linux CUDA by the engine's own parallel defaults (STRATA_BATCH_SELF_COMMIT=1)
- #6392 [Engine] Linux HIP RX 7900 XTX (32 GB RAM, IQ2_XS low-RAM): engine hangs within 4-10 min of sustained serving, verify timeouts, also on 0.1.63
- #6244 [GUI] Changing an option on the model screen silently drops drafting: dflash2 and resets STRATA_RESIDENT_PIN to 0
- #6312 [Benchmark] `strata bench run` marks a v0.2.16 git checkout nonconforming: the commit lookup checks `terminal/.git`
- #6250 [Engine] Arc Pro B70 (xe): server reaches "ready", first request dies with verify flag A wait
- #5937 [Engine] Windows/gfx1030: working set doubles after ordinary serving (19.5 -> 36 GB) and never returns to baseline
- #6156 [Engine] Qwen3.6-35B-A3B on 2x RTX 3060: qwen35moe ignores multi-GPU flags — patch adds a card-1 expert tier, 37.6 → 74.8 tok/s (+97%)
- #6052 [Engine] Equal prompt chunks skip periodic conversation checkpoints (--prompt-cache-every)
- #5756 [Engine] Tool-call value truncated when the model skips a parameter's own </parameter> after a nested pair (Qwen3.8-Flash-Next)
- #6269 [Engine] gfx103x: prompt throughput gaps left by the MMQ removal (dense projections, IQ4_XS down)
- #6264 [Engine] RDNA2 gfx1030: 37% prefill regression persists in 0.1.62 — MoE GEMM gate/up 3.4x slower than 0.1.59
- #6261 [Engine] Run one Flash-Next model across two DGX Sparks
- #6173 [Other] Source setup accepts --context 262144 for Qwen3.6-35B-A3B on a 12 GB card, and the engine then refuses to start
- #6172 [Other] Source build fails when sccache is on PATH: ggml's global RULE_LAUNCH_COMPILE wraps Strata's nvcc compiles
- #6153 [GUI] App Host dies with V8 "Reached heap limit" (JS heap OOM) after ~9 h uptime — repeatedly on Arch Linux
- #6130 [Engine] RX 7900 XTX (gfx1100, Linux), 0.2.15: picture text misread ("STRATA 412" for "STRATA 42") after earlier requests on the default HIP build; the -DSTRATA_MMQ=ON build reads it right
- #6128 [Engine] 0.1.60 on Windows: with --vram-reserve-mib 700 the expert cache grows past the auto size and decode drops to 0.2-42 tok/s on an RTX 4090
- #6111 [Engine] STRATA_OWN_CPU_QUANT=ON (0.2.15 x86_64 default) is ~4% slower than ggml-cpu on AVX2 CPU expert pool decode (IQ3_XXS)
- #6110 [Engine] explicit --layer-split reloads CUDA0 dense weights a second time at startup (0 MiB freed)
- #6086 [Other] Terminal: shell tab completion for the strata command
- #6045 [Engine] SYCL: int8 ESIMD prompt attention fails qsa_prompt_attn_parity on Arc Pro B70
- #6004 [Engine] Prefill hangs on the second prompt chunk, whatever its size (Windows, sm_120, Edge0-120B Q3_K, 0.1.55): watchdog kill 0xC0000409
- #6325 [Engine] RDNA4 16 GB + 6-core CPU, Gyro-S: the automatic PCIe share (0.90) is ~3 % slower than --pcie-frac 1.0; with --spec 6 --draft-conf 0.6 decode is +7.5 %
- #5913 [Engine] qwen35moe 19B-A3B: htod copy overruns a 57,802,752-byte buffer on a specific 19,431-token prompt
- #5822 [Engine] Flash-Next 0.1.58: native QSA indexer (batch) rejects arguments and exits on single-GPU CUDA
- #5767 [Engine] spec-prob verify: alloc-failure fallback to plain sampling is silent (no log) on the production path
- #5738 [Engine] Windows HIP (gfx1030): STRATA_ADAPT_OVERLAP=1 fails the first request with "never rang (unspecified launch failure)" when the whole expert arena is pinned
- #5718 [Engine] gfx1200 (RX 9060, Linux): "verify: timed out" (#267) during decode, not tied to spec decoding, RAM budget or pool workers
- #5654 [Engine] Dual RTX 5060 Ti over OCuLink: Xid 79 during tune auto (0.1.58, Linux driver 615.71.09 open)
- #5635 [Engine] 0.1.58 regression: iq3_s + 256k OOM-killed and --no-tui no longer holds foreground, breaking systemd service
- #5612 [Engine] conversation cache: on a layer split, a sub-agent that matches only a shared head takes the whole parked conversation and drops its checkpoints
- #5608 [Engine] RX 9070 XT gfx1201: repeatable GPU page faults during IQ3_S inference on HIP 0.1.57/0.1.58
- #5559 [Engine] 0.1.58 hip-rx9070 (gfx1201): strata-host crashes repeatedly (GPF in libhsa-runtime64, exit -6/-11) under 35K-92K prompts; 0.1.57 runs clean
- #6389 [Benchmark] 5 x Quadro RTX 8000 (sm_75), DeepSeek-V4.1-Flash IST 2.25 bpw: decode 13.5 to 29.3 tok/s by expert placement and --threads 1
Pull requests
- #6520 [Engine] Inkling-2-Mini from the official NVFP4/MXFP8 checkpoint, expert offload and CPU experts for 8-16 GB cards
- #6315 [Engine] serve: a tool call written in a shape its schema does not declare is read as the call it meant (#6285)
- #6023 [Engine] peer_stream_ring: fix >= 2K peer_i8 ring wraparound + V100 docs
- #6529 [Engine] Volta sm_70 decode optimizations, zero-VRAM in-place Q8_0, NVLink split head, and volta-forever detection
- #6548 [Engine] Add opt-in streamed-KV QSA slot-group batching, pre75 multi-slot attention, and batch SIDE_MIXER
- #6547 [Engine] Add opt-in multi-slot batched MTP drafting (STRATA_BATCH_MTP_FUSED)
- #6546 [Engine] Opt-in resize_for_overwrite and parallel host memcpy for kv_mode != 0 park/restore
- #6545 [Engine] Size STRATA_PARK_ASYNC VRAM stage by device-resident bytes under kv_mode != 0
- #6544 [Engine] Fix O(N^2) scan in getline_fd and avoid full-line copy in BGEN/parse_i64_list
- #6543 [Engine] Guard negative page_table entries in qsa_prompt_attn and track monotonic kv_stream overflow_count
- #4878 [GUI] Keep quiet desktop chat streams alive
- #3553 [Engine] let a HIP helper read pinned expert rows in place
- #3552 [Engine] skip file-tier experts while a helper GPU is attached
- #3551 [Engine] add an opt-in CUDA and HIP hybrid build
- #4551 [Engine] session-file v3: incremental append saves under --session-save-append
- #3800 [Engine] Token mask for JSON response formats: MTP drafts survive constrained decoding
- #5436 [Engine] opt-in STRATA_ARENA_NUMA: place the expert arena per NUMA node on two-socket Linux
- #6506 [Engine] add Inkling 2 model family and dual-GPU looped MoE engine support
- #3607 [Engine] native Windows support for Intel Arc SYCL, rebased onto 0.2.18 (engine 0.1.64)
- #5820 [Engine] Multiple API keys with per-key concurrency limits and reserved capacity
- #6365 [Engine] Prefer FP32 TLA sparse prefill on Battlemage in builds with local TLA headers
- #6514 [Benchmark] RX 7600 XT (gfx1102): ROCm 7.2.4 vs 10.1, and the CachyOS ROCm 10.1 crash
- #6510 [Engine] --experts-wex4: read the routed experts from a checked WEX4 container (opt-in, file tier)
- #4376 [Engine] dsv41: the WMMA expert kernels compile on pre-Volta cards
- #6468 [Benchmark] RX 9070 XT on Windows, Gyro-S at 131K: app 0.2.17 / engine 0.1.63 with a tuned config (standard 12/12)
- #6176 [Engine] q4u32: the 4-bit KV cache with a fitted step as the default on RDNA4
- #4255 [Other] serve: refuse a port another program holds on 127.0.0.1, and say which program
- #6492 [Other] tests: the first VisionTempFiles class was shadowed and never ran
- #6486 [Engine] serve: an mcp__ prefix added to a plain tool, or dropped from an MCP tool, is that tool
- #6485 [Engine] Add experimental gfx90a HIP build
- #6481 [Engine] keep the baked qwen think block when preserve_thinking is unset
- #3957 [Engine] serve: a long conversation survives an engine restart - parked conversations saved at a graceful stop and loaded at the next start, to files or (Windows) kept in RAM with no disk writes (opt-in STRATA_PARK_DIR, STRATA_PARK_RAMLIKE=1; layer split included)
- #6474 [Engine] serve: keep a restarted engine's batch slot state out of old request cleanup
- #6471 [Engine] serve: send STOP when closing a batch admission mid-prompt
- #5179 [GUI] add true same-turn coding-agent steering with a reproducible Harness patch
- #6366 [Engine] Build the Battlemage TLA prompt attention by default from a sycl-tla submodule
- #1614 [Engine] shared KV pool for all lanes (--kv-pool-tokens): at 2 x 256k the first token comes 2-5x sooner and lane moves ~10x faster; off = identical to main
- #6465 [Engine] bound host RAM during conversation swaps
- #6464 [Benchmark] Strix Halo 64 GB unified memory (Ryzen AI Max+ 395)
- #6453 [Engine] SYCL: an integrated Intel GPU is planned as one pool of memory with the system (Arc B390)
- #6391 [Other] verify the context patch on reused desktop Harness stages
- #6458 [Engine] STRATA_FILL_STAGED: copy mapped blobs to the GPU via pinned buffers
- #6455 [Engine] SYCL: an Xe3 GPU (Panther Lake, Arc B390) runs the Battlemage kernels; STRATA_INTEL_GEN sets the class
- #3919 [Engine] kv: size the resident ring from the run's depth (opt-in, STRATA_KV_RING_ADAPT)
- #3729 [Engine] SYCL: flag Intel iGPUs as integrated so the expert cache is sized from MemAvailable
- #3648 [Engine] --peer-device host route: STRATA_PF_PEER_PIECES=1 (opt-in) moves the activations and the sums in 8 pieces (+7 % prompt on 2x V100)
- #6427 [Engine] layer split auto with DFlash2: plan DFlash2's drafter and after-cache bind on the last stage, and keep the gate-off fallback loadable
- #6433 [Engine] Fix: read the MTP draft layer's expert count from experts.bin, to support models with other expert counts such as pruned models
- #6428 [Engine] Count speculative pages once in the macOS free-memory estimate
- #6263 [Engine] Add opt-in MPI/NCCL split inference for two DGX Sparks
- #5901 [Engine] finish tool arguments that quote an unclosed call
- #6424 [Other] tests: isolate the two SYCL-path drafting tests from a real sibling Strata-data
- #4374 [Other] serve: opt-in "system_reminders": "tail" keeps a client's system-reminder blocks at the end of the prompt
- #6418 [Engine] Leave STRATA_BATCH_SELF_COMMIT out of the Linux CUDA parallel defaults when STRATA_PIPED_MTP is asked (#6160)
- #4883 [Other] Setup: --gpus on Windows AMD: RDNA 2, 3 and 4 cards sharing one model
- #6314 [Benchmark] RX 6700 XT and RX 6600 (x1, x2, with and without a rocBLAS table) / Qwen3.8-Flash-Next / IQ3_S / strata-qwen38-thinking-v1-draft.1 on the 0.2.16 rx6000 package
- #4859 [Engine] a 3-bit Lloyd-Max K/V (--kv oct3) with an exact fp16 window, and the gfx1100 decode ports
- #5494 [Other] Windows: recognise the Radeon Pro V620 (PCI id 0x73A1) as gfx1030
- #5504 [Engine] Credit clean active_file cache in the conversation memory guard
- #6166 [Engine] opt-in blob verifier for the direct expert path: STRATA_BLOB_VERIFY
- #6262 [Engine] IQ4_NL down rows in 512-bit lanes, opt-in, same bits as today's paths
- #6249 [Engine] Opt-in STRATA_PREFILL_EQUAL_TAIL: keep a short last prompt chunk instead of a second streamed pass
- #6401 [Engine] oomd_pacer: discover split --native GGUF shards and keep PLE cached without --ple-gguf
- #6087 [Other] Terminal: strata complete prints bash/zsh/fish tab completion from the CLI's own grammar
- #6058 [Other] mtp_fetch: --repo to read the MTP tensors from another repository
- #6034 [Engine] Parked conversations spill to a disk tier instead of being dropped
- #5976 [Other] add opt-in strata-private-files Rust crate for ACL/mode enforcement
- #5975 [Other] add opt-in strata-feed Rust crate for update feed validation
- #5974 [Other] add opt-in Rust strata-transfer crate for streaming SHA-256 verification
- #5973 [Other] add opt-in Rust strata-procs crate for process identity and command-line inspection
- #5972 [Other] add opt-in Rust strata-fit crate for VRAM and multi-GPU fit math
- #5970 [Other] add opt-in Rust strata-sysinfo crate for WMI-free OS facts
- #5835 [Engine] Conversation cache: an opt-in disk tier for evicted, idle and oversized conversations (--conversation-cache-dir)
- #4867 [Engine] HIP/Linux: keep the kernel's NUMA balancing off the engine's memory (GPU queue evictions)
- #5602 [Engine] tests: test_hip_ordinal fails on any machine with an integrated Radeon