[Bugfix] Fix loading Music Flamingo (#35535)

Nick Cao committed 8 months ago

[Bugfix] dtype mismatch in ngram gpu propose (#37246)

PatchyTIS committed 8 months ago

[Refactor] Relocate responses API tests (#37241)

Flora Feng committed 8 months ago

[ROCm] Fix AttributeError for torch.compiler.skip_all_guards_unsafe on older PyTorch (#37219)

Andreas Karatzas committed 8 months ago

[Refactor] Relocate completion and chat completion tests (#37125)

Flora Feng committed 8 months ago

[CI] Fix flaky tool_use chat completion tests with deterministic seed (#37027)

Flora Feng committed 8 months ago

Add ability to replace oot ops when using lora (#37181)

Kyuyeun Kim committed 8 months ago

Support non-contiguous KV cache in TRTLLM fp8 dequant kernel (#36867)

Vadim Gimpelson committed 8 months ago

[BugFix] Correct max memory usage for multiple KV-cache groups (#36030)

Harry Huang committed 8 months ago

Fix some Mistral parser issues (#37209)

Julien Denize committed 8 months ago

[Feature][Frontend] add support for Cohere Embed v2 API (#37074)

Walter Beller-Morales committed 8 months ago

[CI/Build] Add common tool call parser test suite (#27599)

Ben Browning committed 8 months ago

[Custom Ops] Add functional + out variant for scaled_fp4_quant (#34389)

Terry Gao committed 8 months ago

Fix EagleMistralLarge3Model initialization (#37232)

Julien Denize committed 8 months ago

[CI] Stabilize multinode DP internal LB completion tests (#36356)

Andreas Karatzas committed 8 months ago

[Doc] Clarify schema enforcement behavior for tool_choice modes (#37064)

Yuchen Fama committed 8 months ago

[Benchmark] Improvements to attention benchmark script (#37115)

Wei Zhao committed 8 months ago

[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)

EdalatiAli committed 8 months ago

Fix eplb nvfp4 experts hook (#37217)

Elvir Crnčević committed 8 months ago

[Bugfix] opcheck false mutation error in rms_norm_per_block_quant (#36688) (#36779)

Krish Gupta committed 8 months ago