[UX nit] Fix non-default api_server_count message (#34152)

Michael Goin committed 9 months ago

Minor cleanup for Voxtral (#34247)

Andy Lo committed 9 months ago

[Model Runner V2] Use pinned memory for write_contents (#34222)

Woosuk Kwon committed 9 months ago

[Docs] Speed up build environment set-up (#34240)

Harry Mellor committed 9 months ago

[BUGFIX] Fix accuracy bugs in Qwen3-Next MTP (#34077)

Vadim Gimpelson committed 9 months ago

[Core][BugFix] Fix PP KV cache sharding memory validation (#33698)

junuxyz committed 9 months ago

[Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention (#33680)

Roberto L. Castro committed 9 months ago

[compile] Enable AOT compile with 2.10 in trunk. (#34155)

Zhengxu Chen committed 9 months ago

[ROCm][Quantization] GPT_OSS in amd-quark format model loading and emulations (#29008)

xuebwang-amd committed 9 months ago

Support benchmarking of Geospatial models (#33922)

mgazz committed 9 months ago

add --insecure arg to the vllm bench to skip TLS (#34026)

Fan Yang committed 9 months ago

Bump `mamba-ssm` version in CI for Transformers v5 compatibility (#34233)

Harry Mellor committed 9 months ago

[V1][BugFix] Fix EAGLE3 encoder cache miss with disable_chunked_mm_input (#34220)

Krish Gupta committed 9 months ago

Stop testing for slow tokenizers as they will not exist soon (#34235)

Harry Mellor committed 9 months ago

[Misc] allow specify is_mm_prefix_lm in hf_config (#34215)

Phúc H. Lê Khắc committed 9 months ago

Add flagos in MiniCPM-o (#34126)

tc-mb committed 9 months ago

[Bugfix] Fix FI kernel`chunk_gated_delta_rule` output shape for Qwen3.5 (#34219)

Roger Wang committed 9 months ago

[Docs] Fix format error in KV load failure recovery doc (#34137)

zzaebok committed 9 months ago

[Bugfix] Fix `--trust-remote-code` conflict (#34218)

Cyrus Leung committed 9 months ago

[Bugfix] Fix memory inconsistency in cross-process shared memory (#32022)

Zetong Li committed 9 months ago