Open
Conversation
krissetto
force-pushed
the
improve-dmr-support
branch
2 times, most recently
from
2e7bbfe to
a6a876c
Compare
- fixes session title generation - adds 'context_size' provider_opt for DMR usage instead of giving 'max_tokens' double responsibility to avoid confusion - improved thinking budget support and fix for NoThinking() - improves how flags are sent to the DMR model/runtime configuration endpoint - clarify docs on sampling/runtime params Signed-off-by: Christopher Petito <chrisjpetito@gmail.com>
krissetto
force-pushed
the
improve-dmr-support
branch
from
a6a876c to
d2eac5f
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Improve DMR support
provider_opts.context_sizesets the engine's context window; max_tokens stays strictly per-request output instead of pulling-double duty (which was confusing)._configurerequest mirroring model-runner'sBackendConfiguration(context-size, runtime-flags, speculative, llamacpp.reasoning-budget, vllm.{hf-overrides,gpu-memory-utilization}).thinking_budgetrouted properly per backend:reasoning-budgetfor llama.cpp,thinking_token_budgetper-request for vLLM, ignored on MLX/SGLang for now.chat_template_kwargs.enable_thinking=falseprovider_opts.runtime_flags.