mudler/vllm.cpp

View on GitHub

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)

Stars: 423
Forks: 53
Open beginner issues: 0
Indexed issues: 351
Avg merge: 20h 26m
Merged PRs (30d): 310

Dominant language: C++
License: Apache-2.0
Last GitHub push: Sep 20, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

29 beginner-friendly issues open

[32-bit] nvfp4_plan_cache.h fails with size_t narrowing on i586 Open

Difficulty 1/5 Under an hour Newbie friendliness 88/100

mudler/vllm.cpp#3181 · Opened Sep 13, 2026
fix(BACKEND-ROCM-QUANT-GATHER): label the comparison scope from the run, not a literal Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

mudler/vllm.cpp#3126 · Opened Sep 10, 2026
Reject non-finite values in the native HRX numerical comparator Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

mudler/vllm.cpp#3088 · Opened Sep 8, 2026
sync(UPSTREAM-SYNC-HEADPIN): step6-c1a credits the version read to a job whose own read returned 1 Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

mudler/vllm.cpp#2997 · Opened Sep 6, 2026
test_cpu_x86_llamacpp_floor reds as a function of machine load, on branches that never touched it Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

mudler/vllm.cpp#2976 · Opened Sep 5, 2026
#2777 deleted a recorded closed negative along with its stale preamble Open

Difficulty 1/5 Under an hour Newbie friendliness 85/100

mudler/vllm.cpp#2943 · 1 comment · Opened Sep 5, 2026
T36's op gate is not registered in tests/CMakeLists.txt, so it has never been built or run Open

Difficulty 1/5 Under an hour Newbie friendliness 88/100

mudler/vllm.cpp#2937 · Opened Sep 5, 2026
The T34 host-split evidence file the GFX1100-TG200 spec cites was never contributed Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

mudler/vllm.cpp#2936 · Opened Sep 5, 2026
scripts/opt-dgx-gate.sh says it runs the gate series under a flock and never takes one Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

mudler/vllm.cpp#2798 · Opened Sep 3, 2026
port: HY V4 is a post-pin architecture no row owns, and its two shared-file halves are pre-pin holes rather than the distance Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

mudler/vllm.cpp#2735 · Opened Sep 3, 2026
fix(TOOLS-STRUCTURED-CORE): a NUL byte in structured_outputs.regex silently truncates the pattern instead of being rejected Open

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

mudler/vllm.cpp#2701 · Opened Sep 3, 2026
perf(SPEC-GDN-SEGMENTS): the GDN builder computes context_lens on decode-only batches that never read it Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

mudler/vllm.cpp#2696 · Opened Sep 3, 2026
perf(SAMPLE-BEAM): beam search detokenizes every intermediate step it discards Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

mudler/vllm.cpp#2684 · Opened Sep 3, 2026
fix(LOAD-CONFIG-SURFACE): a list-valued num_experts_per_tok makes the whole hf_config parse throw Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

mudler/vllm.cpp#2664 · Opened Sep 3, 2026
fix(KV-PREFIX-MATCH-UNIT): the mamba back-off predicate compares block sizes instead of reading mamba_cache_mode Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

mudler/vllm.cpp#2663 · Opened Sep 3, 2026
record(MODEL-TEXT-qwen3-5-qwen3-5-for-causal-lm): the backbone-prefix comment cites a mapper that does not exist at ad5d29db70 Open

Difficulty 1/5 Under an hour Newbie friendliness 91/100

mudler/vllm.cpp#2654 · Opened Sep 3, 2026
fix(ENG-RUNNER-MODELSHAPE): BlockTable::move_row leaves the vacated source row populated Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

mudler/vllm.cpp#2636 · Opened Sep 3, 2026
The EXL3 device arm labels never print: MESSAGE stringifies a const char* as a bool Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

mudler/vllm.cpp#2587 · Opened Sep 2, 2026
main CI never completes: cancel-in-progress is true for push, so every run is cancelled by the next push (0 successes in 100 runs) Open

Difficulty 1/5 Under an hour Newbie friendliness 84/100

mudler/vllm.cpp#2491 · Opened Sep 1, 2026
ENG-MULTIKV-BYNAME: MultiKvCacheIndex::num_groups()'s comment says it counts attn_kv's groups, and since 9e7621efc it counts every published cache's Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

mudler/vllm.cpp#2459 · Opened Sep 1, 2026
toy_model_plugin's kToyInfo is positional over a ModelInfo whose leading fields are all bool, so a mid-struct insert misassigns SILENTLY Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

mudler/vllm.cpp#2420 · Opened Aug 31, 2026
VT_QWEN35_STAGE_RESERVE_BYTES undocumented — the third env var to red main in two days, and the checker cannot see duplicates Open

bug

Difficulty 1/5 Under an hour Newbie friendliness 88/100

mudler/vllm.cpp#2357 · Opened Aug 30, 2026
check-env-doc is RED on main again: #2349 landed VT_QWEN35_STAGE_RESERVE_BYTES undocumented Open

Difficulty 1/5 Under an hour Newbie friendliness 85/100

mudler/vllm.cpp#2356 · Opened Aug 30, 2026
ModelRegistry::Forward's multi-cache refusal names ONE owner where THREE architectures now arrive, and never names the arriving architecture Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

mudler/vllm.cpp#2353 · Opened Aug 30, 2026
index row for #1954 wrongly claims #907 documents the same test and assertion Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

mudler/vllm.cpp#2013 · Opened Aug 26, 2026
test_backend_cross_device: MoeSiluMul bf16 exactness reds on gfx1200 ROCm too, the ROCm counterpart of #1802 Open

Difficulty 1/5 Under an hour Newbie friendliness 86/100

mudler/vllm.cpp#1954 · 2 comments · Opened Aug 26, 2026
README architecture and ABI claims lag the source Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

mudler/vllm.cpp#1429 · Opened Aug 20, 2026
docs: align README counts with the public registry Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

mudler/vllm.cpp#976 · Opened Aug 16, 2026
Metal build fails: unused const kGdnLayers in test_qwen27n_fp8_tower_paged_engine.cpp Open

Difficulty 1/5 Under an hour Newbie friendliness 92/100

mudler/vllm.cpp#629 · Opened Aug 13, 2026

mudler/vllm.cpp

Get new issues in your inbox