-
Notifications
You must be signed in to change notification settings - Fork 895
Pull requests: FlashML-org/FreeToken
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(scheduler): hybrid radix hit corruption — GDN snapshot copy-on-donate + admission barriers
#287
opened Aug 30, 2026 by
Cerynitius
Loading…
fix(models): load NVFP4 expert banks from checkpoints without a safetensors index
#283
opened Aug 30, 2026 by
paulp83
Loading…
fix(moe): match the benchbw verdict to the served model's expert size
#278
opened Aug 29, 2026 by
bernimccoy
Contributor
Loading…
fix: [BUG] qwen3_5 dense: mixed-precision NVFP4 crashes in ct_bf16_fuse (Float8 × BFloat16 promotion)
#275
opened Aug 29, 2026 by
yuyi2439
Loading…
glm5_next: support GLM-5.3-Flash (hybrid KDA + DSA, mHC, NVFP4 expert offload)
#270
opened Aug 29, 2026 by
Cerynitius
Loading…
fix(server): report why a tokenizer/detokenizer worker died during load
#269
opened Aug 29, 2026 by
sime2408
Loading…
feat(kvcache): sub-byte Q4_0 and Q6_0 KV cache quantization
#268
opened Aug 29, 2026 by
fangyuan-3149
Loading…
fix(server): hide qwen transport markers from semantic responses
#266
opened Aug 29, 2026 by
HaileyStorm
Loading…
fix(build): honor explicit and versioned CUDA toolkits
#264
opened Aug 29, 2026 by
HaileyStorm
Loading…
feat(bench): pass ft serve options through '--' in bench_decode_moe
#254
opened Aug 28, 2026 by
yuyi2439
Loading…
feat(sm70): support Volta / Tesla V100 via torch 2.10 cu128 downgrade
#253
opened Aug 28, 2026 by
itongxiaojun
Loading…
fix(engine): handle torch 2.9 allocator API deprecation
#245
opened Aug 28, 2026 by
fangyuan-3149
Loading…
rocm: fix native extensions, kernel JIT builds, and Triton PTX fallbacks for gfx1150
#241
opened Aug 27, 2026 by
skywalk1411
Loading…
6 of 7 tasks
fix(engine): probe the real WSL pin budget instead of guessing 40% RAM
#233
opened Aug 27, 2026 by
zuver-lab
Loading…
feat(moe): --moe-collect-stats, so expert-cache behaviour is measurable
#231
opened Aug 27, 2026 by
vcruz305
Loading…
feat(server): OpenAI-compatible logprobs for chat and legacy completions
#224
opened Aug 26, 2026 by
Artemowka22
Loading…
3 tasks done
fix(server): validate sampling params and rebuild timeout at the API layer
#223
opened Aug 26, 2026 by
Artemowka22
Loading…
3 tasks done
fix(server): guarantee AbortMsg delivery on stream cancellation
#222
opened Aug 26, 2026 by
Artemowka22
Loading…
2 tasks done
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.